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

    Neuronpedia

    INDEX
    Explanations

    various including

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    く
    0.86
    ap
    0.80
    à
    0.79
    er
    0.76
    å
    0.75
    이나
    0.73
     sembra
    0.73
    ishly
    0.72
    ק
    0.70
    om
    0.70
    POSITIVE LOGITS
     различные
    0.84
     المختلفة
    0.83
     различных
    0.78
    <unused289>
    0.78
    entliche
    0.77
    <unused512>
    0.75
    <unused1870>
    0.74
    <unused2002>
    0.74
    <unused1645>
    0.73
    <unused983>
    0.72
    Act Density 0.008%

    No Known Activations