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

    Neuronpedia

    INDEX
    Explanations

    AI

    np_max-act-logits · gemini-2.0-flash

    Instances where the text refers to the model's identity or system role (system/instruction messages declaring the assistant/AI).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Negative Logits
    Miami
    -0.07
    IFICATION
    -0.07
     popul
    -0.06
     analy
    -0.06
    Snow
    -0.06
    ()).
    -0.06
    nos
    -0.06
    793
    -0.06
     mood
    -0.06
    атель
    -0.06
    POSITIVE LOGITS
     handwritten
    0.06
     coarse
    0.06
     FStar
    0.06
     pravděpodob
    0.06
     geliş
    0.06
    wait
    0.06
    _GO
    0.06
     στι
    0.06
     olabilir
    0.06
    beer
    0.06
    Act Density 0.005%

    No Known Activations