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

    Neuronpedia

    INDEX
    Explanations

    brackets and special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    archy
    -0.07
    ी-
    -0.06
     sealed
    -0.06
    ایی
    -0.06
     Fi
    -0.06
     tiles
    -0.06
    Appearance
    -0.06
     appraisal
    -0.06
     Eva
    -0.06
    рі
    -0.06
    POSITIVE LOGITS
    /of
    0.07
    тон
    0.07
    WithData
    0.07
    <br
    0.07
    [^
    0.06
    нул
    0.06
    نسان
    0.06
    )[-
    0.06
    omm
    0.06
    ريق
    0.06
    Act Density 0.001%

    No Known Activations