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

    Neuronpedia

    INDEX
    Explanations

    vector

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Know
    -0.07
    Hits
    -0.06
    /button
    -0.06
     vidět
    -0.06
    Phill
    -0.06
    Convertible
    -0.06
     náz
    -0.06
     autobiography
    -0.06
     próp
    -0.06
    わけ
    -0.06
    POSITIVE LOGITS
    oretical
    0.07
    .setOnAction
    0.06
    .validators
    0.06
     кор
    0.06
    rise
    0.06
    eous
    0.06
     Mail
    0.06
     Haw
    0.06
    (User
    0.06
     FileStream
    0.06
    Act Density 0.016%

    No Known Activations