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

    Neuronpedia

    INDEX
    Explanations

    origin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     виправивши
    -0.80
     propOrder
    -0.79
    expandindo
    -0.76
     дописавши
    -0.76
    CppMethod
    -0.73
     sureties
    -0.72
     بيها
    -0.72
    ItemLayout
    -0.70
    writeField
    -0.70
     autorytatywna
    -0.69
    POSITIVE LOGITS
     of
    0.51
     point
    0.50
     from
    0.48
     in
    0.47
    rek
    0.46
    keres
    0.44
    [
    0.43
    akal
    0.43
    ant
    0.42
    oc
    0.42
    Act Density 0.006%

    No Known Activations