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

    Neuronpedia

    INDEX
    Explanations

    Neural network initialization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "net
    -0.07
    ListOf
    -0.07
    _mx
    -0.07
     lust
    -0.06
     Ft
    -0.06
     updater
    -0.06
     دقی
    -0.06
    .include
    -0.06
    ambil
    -0.06
    ldre
    -0.06
    POSITIVE LOGITS
    464
    0.07
    934
    0.06
    829
    0.06
     bowls
    0.06
    [],
    0.06
     humiliation
    0.06
    コ
    0.06
    767
    0.06
    영
    0.06
    ,↵
    0.06
    Act Density 0.004%

    No Known Activations