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

    Neuronpedia

    INDEX
    Explanations

    Oracle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    entieth
    -0.07
    (in
    -0.07
     거
    -0.06
    (getActivity
    -0.06
    苦
    -0.06
     famine
    -0.06
     imdb
    -0.06
     cJSON
    -0.06
     {:.
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     surrendered
    0.07
     resid
    0.07
     Oracle
    0.07
    ラク
    0.07
     japan
    0.07
     Anaheim
    0.06
    戶
    0.06
     HP
    0.06
     może
    0.06
    ernen
    0.06
    Act Density 0.000%

    No Known Activations