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
    	comment
    -0.08
    COMMENT
    -0.07
     userAgent
    -0.07
    -ste
    -0.06
     holders
    -0.06
    feed
    -0.06
    sharing
    -0.06
     kính
    -0.06
     Spears
    -0.06
    哭
    -0.06
    POSITIVE LOGITS
     tussen
    0.06
     Ak
    0.06
     fantastic
    0.06
     počtu
    0.06
     Kontakt
    0.06
     работа
    0.06
    Ğ
    0.06
     شمالی
    0.05
    explained
    0.05
    ":"","
    0.05
    Act Density 0.381%

    No Known Activations