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

    Neuronpedia

    INDEX
    Explanations

    percorso, durante, dopo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ası
    0.87
    ի
    0.81
    ो
    0.80
    у
    0.80
    u
    0.79
    ا
    0.79
    다
    0.77
    en
    0.75
    पूर
    0.75
    asına
    0.73
    POSITIVE LOGITS
     n
    0.80
     percorso
    0.76
     v
    0.69
    0.69
    F
    0.69
    ，
    0.67
     h
    0.66
     durante
    0.66
     dopo
    0.66
     kako
    0.66
    Act Density 0.004%

    No Known Activations