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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     effected
    -0.07
    _lvl
    -0.07
    '].'/
    -0.07
     prostřed
    -0.06
    (pro
    -0.06
    .ComboBox
    -0.06
     strategic
    -0.06
     Transformer
    -0.06
     한번
    -0.06
     Hector
    -0.06
    POSITIVE LOGITS
    _last
    0.07
     datetime
    0.07
     Om
    0.06
     digital
    0.06
     mocking
    0.06
    ись
    0.06
    "log
    0.06
    ،↵
    0.06
    消
    0.06
    الس
    0.06
    Act Density 0.004%

    No Known Activations