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

    Neuronpedia

    INDEX
    Explanations

    code comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     particularly
    -0.08
    osition
    -0.07
     grow
    -0.07
     abroad
    -0.07
     notable
    -0.07
    	transform
    -0.07
     прилож
    -0.07
     transform
    -0.07
    .apps
    -0.07
    g
    -0.07
    POSITIVE LOGITS
     মন্তব্য
    0.12
     комментар
    0.12
     Kommentare
    0.11
     comentário
    0.11
     kommentar
    0.11
    Комментар
    0.10
    は禁止
    0.10
    コメント
    0.10
     COMMENTS
    0.10
    Комментарии
    0.10
    Act Density 0.003%

    No Known Activations