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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    òi
    -0.07
    له
    -0.06
    분
    -0.06
    OUNTER
    -0.06
    _HOLD
    -0.06
    .Pro
    -0.06
     AG
    -0.06
    zeň
    -0.06
    -described
    -0.06
     вес
    -0.06
    POSITIVE LOGITS
    (mContext
    0.08
    Orientation
    0.07
    kin
    0.07
     nedeni
    0.07
    andom
    0.06
     内
    0.06
     notify
    0.06
     κάθε
    0.06
    inston
    0.06
    rodní
    0.06
    Act Density 0.002%

    No Known Activations