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

    Neuronpedia

    INDEX
    Explanations

    URL

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ADE
    -0.07
    於
    -0.07
     Hearts
    -0.06
     시험
    -0.06
     Landscape
    -0.06
     behaviour
    -0.06
    (before
    -0.06
    иг
    -0.06
    jejer
    -0.06
    Children
    -0.06
    POSITIVE LOGITS
    ISTR
    0.06
     Chan
    0.06
    coli
    0.06
    GN
    0.06
    .Socket
    0.06
    baseUrl
    0.06
    907
    0.06
    iedy
    0.06
     baseURL
    0.05
     */,↵
    0.05
    Act Density 0.014%

    No Known Activations