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

    Neuronpedia

    INDEX
    Explanations

    save

    np_max-act · gemini-2.0-flash

    The neuron is selectively activating on numeric and numeric‐related tokens (e.g. dice expressions, DCs, ability‐score numbers, saving‐throw values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    れる
    -0.07
     durum
    -0.06
     бути
    -0.06
    vette
    -0.06
    _na
    -0.06
     مصرف
    -0.06
    (strcmp
    -0.06
    (cc
    -0.06
     батьків
    -0.06
     Utah
    -0.06
    POSITIVE LOGITS
    >I
    0.07
    opyright
    0.07
    pieces
    0.06
    асти
    0.06
    ��
    0.06
    loff
    0.06
    reply
    0.06
     clicking
    0.06
     jdbcTemplate
    0.06
    macro
    0.06
    Act Density 0.004%

    No Known Activations