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

    Neuronpedia

    INDEX
    Explanations

    object, instance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ecn
    -0.08
     الثالث
    -0.07
    (bundle
    -0.06
     addSubview
    -0.06
    ในป
    -0.06
    Occurrences
    -0.06
    acin
    -0.06
    mid
    -0.06
    /TR
    -0.06
     Mobility
    -0.06
    POSITIVE LOGITS
     Pf
    0.07
    <GameObject
    0.07
     Check
    0.06
    .Tensor
    0.06
     постанов
    0.06
     Fires
    0.06
     وكانت
    0.06
    cción
    0.06
    zz
    0.06
    getState
    0.06
    Act Density 0.020%

    No Known Activations