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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .GetName
    -0.07
    )$
    -0.06
     beğ
    -0.06
     Participation
    -0.06
    详情
    -0.06
     itemId
    -0.06
     Navigation
    -0.06
    _event
    -0.06
     ב
    -0.06
    em
    -0.06
    POSITIVE LOGITS
    自然界
    0.08
     overthrow
    0.07
    _protocol
    0.07
     CIA
    0.07
    𬘡
    0.07
     antenna
    0.07
    าศ
    0.07
    compass
    0.07
    IFORM
    0.07
    .encoder
    0.06
    Act Density 0.001%

    No Known Activations