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

    Neuronpedia

    INDEX
    Explanations

    computer settings

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens—especially floating‐point numbers with decimal points.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .ke
    -0.07
    Query
    -0.07
    ImageButton
    -0.06
    ecided
    -0.06
     ';
    -0.06
    tele
    -0.06
    	q
    -0.06
    slack
    -0.06
     menn
    -0.06
    女性
    -0.06
    POSITIVE LOGITS
     cadena
    0.06
    .locals
    0.06
    :before
    0.06
    ー�
    0.06
    .US
    0.06
     Tòa
    0.06
     accidentally
    0.06
    _BOTTOM
    0.06
     velk
    0.06
     آمریک
    0.06
    Act Density 0.046%

    No Known Activations