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

    Neuronpedia

    INDEX
    Explanations

    words and phrases from personal blog posts and email subscription forms

    oai_token-act-pair · gemini-2.0-flash

    email signups

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sidemargin
    -0.65
    )";
    -0.62
    '},
    -0.59
    setVerticalGroup
    -0.56
     autorytatywna
    -0.56
    LikeLiked
    -0.55
    })));
    -0.54
    StoryboardSegue
    -0.54
    ivably
    -0.53
    )");
    -0.53
    POSITIVE LOGITS
     pil
    0.52
    олові
    0.52
    DJANGO
    0.49
    decorate
    0.48
    abancı
    0.47
     modelleri
    0.46
     Bring
    0.46
    辉
    0.46
    ich
    0.45
    RTGC
    0.45
    Act Density 15.778%

    No Known Activations