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

    Neuronpedia

    INDEX
    Explanations

    SSL security

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ♥
    -0.07
    Mas
    -0.06
     crack
    -0.06
    954
    -0.06
    DIM
    -0.06
    Dash
    -0.06
     Hoa
    -0.06
     collectively
    -0.06
    XXX
    -0.06
    ความ
    -0.06
    POSITIVE LOGITS
    .ly
    0.06
     alphabetical
    0.06
    /moment
    0.06
     posted
    0.06
    .addAction
    0.06
    .script
    0.06
    kins
    0.06
    抜
    0.06
     nude
    0.06
     Vander
    0.06
    Act Density 0.013%

    No Known Activations