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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iode
    -0.07
     ",");↵
    -0.07
    変わ
    -0.07
    _FieldOffsetTable
    -0.06
     forts
    -0.06
    .Bunifu
    -0.06
    Msg
    -0.06
     bona
    -0.06
     interiors
    -0.06
    ('')↵
    -0.06
    POSITIVE LOGITS
    ка
    0.07
     rock
    0.07
    hal
    0.06
     Akron
    0.06
     diagnose
    0.06
    择
    0.06
     Kra
    0.06
     Luz
    0.06
    '];?>
    0.06
     reconstructed
    0.06
    Act Density 0.023%

    No Known Activations