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

    Neuronpedia

    INDEX
    Explanations

    youtube watch links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     сва
    0.44
    ڕۆ
    0.41
     числа
    0.40
     чисел
    0.39
    छ
    0.39
     bald
    0.39
    BOT
    0.38
    मित
    0.38
    Italian
    0.37
     mãe
    0.37
    POSITIVE LOGITS
     Annotation
    0.53
     Annot
    0.46
    annotation
    0.44
    犟
    0.43
     End
    0.43
    Annotation
    0.43
     Stem
    0.42
     annotation
    0.41
    annotations
    0.40
     annotate
    0.40
    Act Density 0.003%

    No Known Activations