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

    Neuronpedia

    INDEX
    Explanations

    mild exclamations of frustration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;
    0.74
     you
    0.67
     ó
    0.58
    ?
    0.57
    ).
    0.56
     bạn
    0.55
     Cry
    0.55
     e
    0.54
     với
    0.54
     ultricies
    0.53
    POSITIVE LOGITS
    Liens
    0.61
    нему
    0.61
    u
    0.61
    Meu
    0.59
    ISTS
    0.59
    GameOver
    0.59
    GLuint
    0.59
    Ｍ
    0.59
    হাম
    0.58
    $\--
    0.58
    Act Density 0.003%

    No Known Activations