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

    Neuronpedia

    INDEX
    Explanations

    ly

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens involved in numeric or price‐style notations (numbers, decimals, dates, currency amounts, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (and
    -0.07
    вали
    -0.07
     meat
    -0.06
     $$$
    -0.06
    omm
    -0.06
    abd
    -0.06
    -checked
    -0.06
    _exist
    -0.06
    icity
    -0.06
    unders
    -0.06
    POSITIVE LOGITS
     sponsor
    0.07
     Hamas
    0.06
     systemd
    0.06
     NOP
    0.06
     соответствии
    0.06
    ¬
    0.06
     Tradable
    0.06
     Geography
    0.06
     Під
    0.06
     تصم
    0.06
    Act Density 0.124%

    No Known Activations