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

    Neuronpedia

    INDEX
    Explanations

    rolling nouns and verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    не
    1.55
    י
    1.41
    ла
    1.33
    ה
    1.32
    '
    1.20
    ी
    1.19
    ت
    1.16
    ی
    1.15
    ک
    1.15
    یی
    1.13
    POSITIVE LOGITS
     Roll
    1.41
    Roll
    1.38
     Rolling
    1.34
     roll
    1.29
     ROLL
    1.24
     Rol
    1.19
    };
    1.17
    Y
    1.14
    Rolling
    1.13
    ROLL
    1.10
    Act Density 0.010%

    No Known Activations