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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ser
    -0.07
    _MUTEX
    -0.06
     refine
    -0.06
     уз
    -0.06
    _projection
    -0.06
    _qp
    -0.06
    َك
    -0.06
    >(()
    -0.06
    "encoding
    -0.06
     amigos
    -0.06
    POSITIVE LOGITS
    God
    0.07
     proximity
    0.07
    Pink
    0.07
    ushi
    0.07
     instituted
    0.07
     offense
    0.07
    持ち
    0.06
    姿
    0.06
    猫
    0.06
    製
    0.06
    Act Density 0.000%

    No Known Activations