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

    Neuronpedia

    INDEX
    Explanations

    word

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric quantity specifications and related words (e.g. numbers and “words” in “1 to 3 words” constraints).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -0.07
     indo
    -0.07
    ICA
    -0.07
    уже
    -0.07
    .Areas
    -0.07
    undo
    -0.07
     mohl
    -0.07
     تحت
    -0.06
     ///
    -0.06
     stringWithFormat
    -0.06
    POSITIVE LOGITS
     Junk
    0.07
     Emblem
    0.06
    Refs
    0.06
     FLOAT
    0.06
    delay
    0.06
     avail
    0.06
    JP
    0.05
    %'↵
    0.05
    unistd
    0.05
    τί
    0.05
    Act Density 0.017%

    No Known Activations