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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    This neuron detects ordinal sequence words (e.g., “first,” “second,” “third,” etc.) indicating steps or positions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    --+
    -0.08
    kového
    -0.07
    /interface
    -0.07
     هایی
    -0.07
    ＿＿＿＿＿＿＿＿
    -0.06
    000
    -0.06
     three
    -0.06
    skými
    -0.06
     six
    -0.06
    埃
    -0.06
    POSITIVE LOGITS
     ΕΛ
    0.07
    량
    0.06
     pev
    0.06
    _);↵
    0.06
     Παρ
    0.06
     pornô
    0.06
     správ
    0.06
     avan
    0.06
    ieron
    0.06
     nivel
    0.06
    Act Density 0.093%

    No Known Activations