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

    Neuronpedia

    INDEX
    Explanations

    given

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Strings
    -0.07
    nosis
    -0.06
     Paras
    -0.06
     invocation
    -0.06
     الأد
    -0.06
     fortunes
    -0.06
    ：
    -0.06
    -screen
    -0.06
     лич
    -0.06
    frage
    -0.06
    POSITIVE LOGITS
    ?>;↵
    0.07
    ildi
    0.07
    .rmtree
    0.07
    辰
    0.06
     міг
    0.06
    پس
    0.06
    weathermap
    0.06
    groupBox
    0.06
    _teacher
    0.06
    .executeUpdate
    0.06
    Act Density 0.005%

    No Known Activations