Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    uncertainty

    np_max-act · gemini-2.0-flash

    This neuron fires on language that discusses uncertainty and the limitations or constraints of a system or model.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    concepts related to frameworks and methodologies in reinforcement learning decision-making processes.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Throws
    -0.06
     Banana
    -0.06
     sixty
    -0.06
     propiedad
    -0.06
    安全
    -0.06
    اذا
    -0.06
    Bien
    -0.06
     ﾞ
    -0.06
     Area
    -0.06
    description
    -0.06
    POSITIVE LOGITS
    _VERSION
    0.07
    .loading
    0.06
     skirt
    0.06
     motor
    0.06
    -platform
    0.06
     기본
    0.06
     contour
    0.06
    PMC
    0.06
    ilerden
    0.06
     Snowden
    0.06
    Act Density 0.010%

    No Known Activations