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

    Neuronpedia

    INDEX
    Explanations

    or/punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plagiar
    -0.07
    лює
    -0.06
     Yourself
    -0.06
     thức
    -0.06
    <Route
    -0.06
    联系
    -0.06
     jumped
    -0.06
     При
    -0.06
    ΕΠ
    -0.06
    ighton
    -0.06
    POSITIVE LOGITS
     ladies
    0.06
    =".$
    0.06
    .hom
    0.06
    جموع
    0.06
    ’
    0.06
     defective
    0.06
     듣
    0.06
     différents
    0.06
    .Peek
    0.06
    HEY
    0.06
    Act Density 0.022%

    No Known Activations