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

    Neuronpedia

    INDEX
    Explanations

    Math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .innerHTML
    -0.07
    るために
    -0.07
    県
    -0.07
    🧒
    -0.07
    👤
    -0.07
    明ら
    -0.07
    toHave
    -0.07
    .ToDouble
    -0.07
    [index
    -0.07
    /small
    -0.06
    POSITIVE LOGITS
    设立
    0.08
    兑现
    0.08
     artış
    0.07
    Registrar
    0.07
     participant
    0.07
     Scarlet
    0.07
    nature
    0.07
    站
    0.07
     resets
    0.07
     GNOME
    0.07
    Act Density 0.018%

    No Known Activations