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

    Neuronpedia

    INDEX
    Explanations

    the key word issue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ко
    0.50
    Ста
    0.49
    Ч
    0.45
    Ш
    0.45
    На
    0.43
    Не
    0.43
    الك
    0.42
     तुमच्या
    0.41
    Ак
    0.41
    NASA
    0.41
    POSITIVE LOGITS
     motto
    0.53
     trio
    0.53
     bölüm
    0.51
     duo
    0.51
     versatile
    0.48
     subroutine
    0.48
     synergistic
    0.47
     flagship
    0.47
     anthology
    0.45
     alanı
    0.45
    Act Density 0.119%

    No Known Activations