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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disappearing
    -0.07
    predictions
    -0.07
    _vs
    -0.06
    /play
    -0.06
     unauthorized
    -0.06
    processor
    -0.06
    视
    -0.06
    _Z
    -0.06
     участь
    -0.06
    .viewModel
    -0.06
    POSITIVE LOGITS
    ικα
    0.07
    wchar
    0.06
     كنت
    0.06
    .Visibility
    0.06
    ัวเอง
    0.06
     dialogRef
    0.06
     poru
    0.06
     Zaman
    0.06
     �
    0.06
    ouser
    0.06
    Act Density 0.001%

    No Known Activations