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

    Neuronpedia

    INDEX
    Explanations

    answering questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tox
    -0.06
     Mines
    -0.06
     scroll
    -0.06
    <R
    -0.06
     Bos
    -0.06
    -sup
    -0.06
     hy
    -0.06
     shutter
    -0.06
    _RADIO
    -0.06
    city
    -0.06
    POSITIVE LOGITS
    duto
    0.08
    aturity
    0.07
     Safe
    0.07
    óng
    0.06
    注意
    0.06
    ANDING
    0.06
    чук
    0.06
    Dating
    0.06
    .IntegerField
    0.06
    ูนย
    0.06
    Act Density 0.047%

    No Known Activations