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

    Neuronpedia

    INDEX
    Explanations

    soy sauce

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oires
    1.01
    a
    0.97
    ља
    0.95
    се
    0.90
    س
    0.89
    ле
    0.88
    То
    0.88
    ی
    0.88
    сот
    0.87
    आन
    0.86
    POSITIVE LOGITS
     highly
    0.74
     równ
    0.74
     afirmar
    0.74
     ‘
    0.73
     sutures
    0.73
     routed
    0.73
     storied
    0.73
    ↵
    0.72
     increasingly
    0.71
     channeled
    0.71
    Act Density 0.002%

    No Known Activations