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

    Neuronpedia

    INDEX
    Explanations

    v

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     olanlar
    -0.07
    “There
    -0.07
    ارية
    -0.07
    .Selenium
    -0.06
    qing
    -0.06
     Donetsk
    -0.06
     leží
    -0.06
    ulace
    -0.06
    .VisualStudio
    -0.06
     november
    -0.06
    POSITIVE LOGITS
    .rate
    0.07
    ทร
    0.07
     prom
    0.07
     tolerated
    0.06
    .detail
    0.06
    815
    0.06
    Four
    0.06
     Fam
    0.06
    aud
    0.06
     angl
    0.06
    Act Density 0.000%

    No Known Activations