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

    Neuronpedia

    INDEX
    Explanations

    Accusations against someone

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numeric tokens—dates, times, measurements, and other number strings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    isters
    -0.07
    ROUGH
    -0.07
    related
    -0.07
    備
    -0.07
     Phó
    -0.06
    ![
    -0.06
     Nutzung
    -0.06
    para
    -0.06
    ंय
    -0.06
    RETURN
    -0.06
    POSITIVE LOGITS
    (auth
    0.07
    ialis
    0.07
    jandro
    0.07
    .tile
    0.06
     Dez
    0.06
    maxlength
    0.06
    uxt
    0.06
    ��
    0.06
    _unc
    0.06
    -strokes
    0.06
    Act Density 0.017%

    No Known Activations