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

    Neuronpedia

    INDEX
    Explanations

    Matcher

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    ?>↵↵↵
    -0.07
    _Metadata
    -0.06
    토
    -0.06
    иты
    -0.06
     보
    -0.06
     Sender
    -0.06
     comme
    -0.06
    ené
    -0.06
     emperor
    -0.06
    POSITIVE LOGITS
     Unfortunately
    0.07
    RetVal
    0.06
     ústav
    0.06
    _alert
    0.06
     submitting
    0.06
     libertarian
    0.06
    üş
    0.06
     зміни
    0.06
     마법
    0.06
     부분
    0.06
    Act Density 0.009%

    No Known Activations