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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _scheme
    -0.07
    .Core
    -0.06
     chairs
    -0.06
    sville
    -0.06
     CODE
    -0.06
     sessionFactory
    -0.06
     Decompiled
    -0.06
    arel
    -0.06
    لمان
    -0.06
     deutschen
    -0.06
    POSITIVE LOGITS
     ],↵
    0.07
    户
    0.07
     applying
    0.06
    today
    0.06
    르고
    0.06
     مشکل
    0.06
    [S
    0.06
     가져
    0.06
     appear
    0.06
    [X
    0.06
    Act Density 0.000%

    No Known Activations