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

    Neuronpedia

    INDEX
    Explanations

    AM, N1, Principal, Cause, test, train leaves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Español
    0.87
     críticos
    0.85
     Восто
    0.85
     trabalhadores
    0.85
     Что
    0.83
     Возможно
    0.83
    ália
    0.82
    ມ
    0.82
    рованный
    0.82
     Datensch
    0.81
    POSITIVE LOGITS
    。
    0.90
    ,\
    0.75
    ，
    0.74
    (\
    0.72
    enseignement
    0.70
    >
    0.67
    },
    0.65
    *
    0.65
    و
    0.64
    ।
    0.64
    Act Density 0.001%

    No Known Activations