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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.69
    AntiForgeryToken
    -0.63
    alleri
    -0.62
    رشف
    -0.61
     quarries
    -0.57
     conserve
    -0.56
    Tracce
    -0.56
     Op
    -0.56
    Avo
    -0.56
    hige
    -0.56
    POSITIVE LOGITS
     begins
    0.57
    ModelAdmin
    0.53
     begint
    0.45
    thodoxy
    0.42
     незавершена
    0.42
     commences
    0.41
     beginnt
    0.41
    asticity
    0.40
     Begins
    0.40
    )__
    0.40
    Act Density 0.022%

    No Known Activations