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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Faction
    -0.06
     También
    -0.06
    (Random
    -0.06
     Roof
    -0.06
    データ
    -0.06
    acted
    -0.06
    teří
    -0.06
     एस
    -0.06
     Sexual
    -0.06
     Turbo
    -0.06
    POSITIVE LOGITS
    obb
    0.06
     dame
    0.06
    538
    0.06
    _pic
    0.06
    etSocketAddress
    0.06
     APA
    0.06
    606
    0.06
     Otherwise
    0.06
    _cs
    0.06
    ,&
    0.06
    Act Density 0.173%

    No Known Activations