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

    Neuronpedia

    INDEX
    Explanations

    to destinations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    teilung
    1.08
     shabby
    1.07
    торы
    1.02
    regation
    1.02
    ء
    1.02
     forcément
    1.01
    ᴄ
    0.98
     ANON
    0.98
    точные
    0.97
    นั้น
    0.97
    POSITIVE LOGITS
    ।
    1.62
    。
    1.49
    en
    1.44
    ;
    1.30
    et
    1.23
    ни
    1.23
    ो
    1.23
    ’
    1.18
    ie
    1.16
    ون
    1.15
    Act Density 0.025%

    No Known Activations