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

    Neuronpedia

    INDEX
    Explanations

    common english words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    endid
    -0.07
    허
    -0.07
    lv
    -0.07
     Throne
    -0.06
     memnun
    -0.06
    Creative
    -0.06
     enlightenment
    -0.06
    /simple
    -0.06
     Himself
    -0.06
     otras
    -0.06
    POSITIVE LOGITS
    _failed
    0.07
    Quest
    0.06
    ??↵↵
    0.06
    instrument
    0.06
    final
    0.06
     fitting
    0.06
    č
    0.06
    ptime
    0.06
    documentation
    0.05
     gab
    0.05
    Act Density 0.000%

    No Known Activations