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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ferm
    -0.07
     jeszcze
    -0.07
     查
    -0.07
     QFile
    -0.06
     MILF
    -0.06
    _dictionary
    -0.06
    iphertext
    -0.06
    ermint
    -0.06
    Length
    -0.06
    .Flag
    -0.06
    POSITIVE LOGITS
    audi
    0.06
    ς
    0.06
    keh
    0.06
    /log
    0.06
    션
    0.06
    @(
    0.06
     anti
    0.06
    17
    0.06
    译
    0.06
    اس
    0.06
    Act Density 0.007%

    No Known Activations