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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Goth
    -0.07
    -wall
    -0.07
    _DISABLED
    -0.06
     evasion
    -0.06
    Aw
    -0.06
    bots
    -0.06
    하면
    -0.06
    usage
    -0.06
    awl
    -0.06
    opers
    -0.06
    POSITIVE LOGITS
     Scalars
    0.07
    ��作
    0.07
     Scalar
    0.07
    人間
    0.06
    ，在
    0.06
    .head
    0.06
    (current
    0.06
     posX
    0.06
    操作
    0.06
    ็ก
    0.06
    Act Density 0.019%

    No Known Activations