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

    Neuronpedia

    INDEX
    Explanations

    multilingual texts

    np_acts-logits-general · gemini-2.5-flash-lite

    Filipino, Portuguese, Spanish, Italian, Romance, Slavic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    K
    0.82
    G
    0.82
    T
    0.80
    e
    0.79
    Y
    0.78
    the
    0.75
    V
    0.75
    W
    0.74
    i
    0.73
    U
    0.73
    POSITIVE LOGITS
     vaše
    0.75
     você
    0.73
     vás
    0.70
     când
    0.69
     tendrás
    0.67
     když
    0.67
     vám
    0.66
     szolgált
    0.66
     számos
    0.66
    át
    0.65
    Act Density 0.000%

    No Known Activations