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

    Neuronpedia

    INDEX
    Explanations

    lists, calculations, or explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     महिन
    0.89
    াবের
    0.89
     खासतौर
    0.86
     Comput
    0.86
    澫
    0.86
    ভাব
    0.85
    っていない
    0.83
    忶
    0.83
    ingen
    0.83
     Акысыз
    0.82
    POSITIVE LOGITS
     racking
    0.71
    📊
    0.70
     វា
    0.70
    iste
    0.69
     nó
    0.69
    🌸
    0.67
    ារ
    0.66
    📝
    0.66
     इसका
    0.65
     salió
    0.64
    Act Density 0.000%

    No Known Activations