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

    Neuronpedia

    INDEX
    Explanations

    step

    np_max-act · gemini-2.0-flash

    This neuron responds to floating-point numeric tokens (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     cult
    -0.07
     Maurice
    -0.06
     detected
    -0.06
     UUID
    -0.06
    /********************************************************
    -0.06
    496
    -0.06
    avit
    -0.06
    (album
    -0.06
    amer
    -0.06
     nen
    -0.06
    POSITIVE LOGITS
     step
    0.14
    Step
    0.14
    step
    0.14
     Step
    0.12
    .Step
    0.12
     STEP
    0.11
    .step
    0.11
     steps
    0.11
     Stephen
    0.11
    _step
    0.10
    Act Density 0.044%

    No Known Activations