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

    Neuronpedia

    INDEX
    Explanations

    import

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    astered
    -0.07
    تبه
    -0.06
     Malta
    -0.06
    िश
    -0.06
    .dy
    -0.06
    uell
    -0.06
    وى
    -0.06
     flirting
    -0.06
    uggy
    -0.05
    ddit
    -0.05
    POSITIVE LOGITS
     INSERT
    0.07
     rapper
    0.07
    ner
    0.07
     /*!↵
    0.07
     Jessie
    0.07
     tooth
    0.07
    Chris
    0.06
     GetString
    0.06
     Traverse
    0.06
    rip
    0.06
    Act Density 0.026%

    No Known Activations