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
     ท
    -0.08
     anderen
    -0.07
     Dios
    -0.07
     *
    -0.06
    -wh
    -0.06
    ;?>
    -0.06
    }{$
    -0.06
    _ENDPOINT
    -0.06
     Cheat
    -0.06
     maison
    -0.06
    POSITIVE LOGITS
    icaid
    0.07
     кам
    0.06
     stealth
    0.06
     сент
    0.06
     spacer
    0.06
     helt
    0.06
     आपक
    0.06
    Commit
    0.06
    Ai
    0.06
    .strictEqual
    0.06
    Act Density 0.003%

    No Known Activations