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

    Neuronpedia

    INDEX
    Explanations

    would

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    р
    -0.07
    (vec
    -0.06
    %s
    -0.06
    市
    -0.06
    .COLUMN
    -0.06
    ず
    -0.06
    _sat
    -0.06
     iterable
    -0.06
     ImportError
    -0.06
    ま
    -0.06
    POSITIVE LOGITS
     işlem
    0.07
     Griffin
    0.07
     Ampl
    0.07
    pre
    0.06
    -controller
    0.06
    ‌‌
    0.06
    _snapshot
    0.06
     NON
    0.06
     WAV
    0.06
    .DeepEqual
    0.06
    Act Density 0.038%

    No Known Activations