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

    Neuronpedia

    INDEX
    Explanations

    %)

    np_max-act · gemini-2.0-flash

    The neuron activates on decimal numeric values (e.g. floating‐point numbers or percentages) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Provider
    -0.06
     spanking
    -0.06
     "~
    -0.06
    "↵↵↵↵
    -0.06
     Tea
    -0.06
     Kerry
    -0.06
     titulo
    -0.06
    >↵↵↵
    -0.06
     shifting
    -0.06
    (li
    -0.06
    POSITIVE LOGITS
    udded
    0.07
     Painter
    0.06
     Cumhurbaşkanı
    0.06
    �
    0.06
     SAN
    0.06
    *this
    0.06
    Utc
    0.06
     Prahy
    0.06
     rightfully
    0.06
    (ok
    0.06
    Act Density 0.009%

    No Known Activations