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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mountain
    -0.07
     formidable
    -0.07
    ѡ
    -0.07
     películ
    -0.07
    amodel
    -0.07
     Location
    -0.07
     rival
    -0.06
     expert
    -0.06
    ѳ
    -0.06
    fol
    -0.06
    POSITIVE LOGITS
     SignIn
    0.07
     الأي
    0.07
    切り
    0.07
    .Dropout
    0.07
     Bảo
    0.07
    ьер
    0.07
    _press
    0.07
    سس
    0.07
    itial
    0.07
    侣
    0.07
    Act Density 0.111%

    No Known Activations