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

    Neuronpedia

    INDEX
    Explanations

    help

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ORIGINAL
    -0.07
    reta
    -0.07
    (down
    -0.06
     Premi
    -0.06
    ẳng
    -0.06
     scares
    -0.06
    ANE
    -0.06
    _general
    -0.06
    esp
    -0.06
     attend
    -0.06
    POSITIVE LOGITS
    ूं
    0.07
     kırmızı
    0.07
    (off
    0.07
    [w
    0.06
     CSP
    0.06
     NotImplementedException
    0.06
    PlainText
    0.06
     refugees
    0.06
     nextPage
    0.06
     Sustainable
    0.06
    Act Density 0.041%

    No Known Activations