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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     apps
    -0.07
    HQ
    -0.06
    GES
    -0.06
     کاهش
    -0.06
    Bush
    -0.06
     Trail
    -0.06
    quivo
    -0.06
    erto
    -0.06
     Oaks
    -0.06
     builders
    -0.06
    POSITIVE LOGITS
     Gina
    0.06
     fined
    0.06
    lanması
    0.06
    .insertBefore
    0.06
    (enabled
    0.06
     hovered
    0.06
    +$
    0.06
    性
    0.06
     tema
    0.06
    -fit
    0.06
    Act Density 0.074%

    No Known Activations