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

    Neuronpedia

    INDEX
    Explanations

    ; followed by i

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lauder
    0.88
    ደም
    0.87
    followlike
    0.87
    ྵ
    0.87
    CodeDict
    0.86
    зидента
    0.86
    த்தக்க
    0.83
    èmes
    0.83
    ॠ
    0.83
    ссмо
    0.83
    POSITIVE LOGITS
     ;
    1.12
    ;
    0.95
     i
    0.92
    .;
    0.87
     overwhelmed
    0.83
     ;)
    0.80
    ؛
    0.79
     s
    0.78
     and
    0.76
     ar
    0.75
    Act Density 0.029%

    No Known Activations