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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     demographics
    -0.07
     wholesalers
    -0.07
    _delete
    -0.07
     ولد
    -0.06
    ilinear
    -0.06
    Tbl
    -0.06
    За
    -0.06
    <SpriteRenderer
    -0.06
    -reaching
    -0.06
     requis
    -0.06
    POSITIVE LOGITS
     glossy
    0.07
     dol
    0.06
    nodiscard
    0.06
     PPP
    0.06
     دول
    0.06
     발
    0.06
     им
    0.06
    $app
    0.06
    /ic
    0.06
     Cham
    0.06
    Act Density 0.027%

    No Known Activations