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

    Neuronpedia

    INDEX
    Explanations

    pioneering approaches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     éxito
    0.38
    離
    0.38
     getters
    0.37
     whenever
    0.37
     दिखाया
    0.36
    whenever
    0.36
     AF
    0.36
    িক্স
    0.35
    EOF
    0.35
    ¹)
    0.35
    POSITIVE LOGITS
     places
    0.45
     द्रविड़
    0.42
    ઉન
    0.41
    퇸
    0.40
     ያሉ
    0.40
    LocalizedString
    0.40
     soglas
    0.39
    তান
    0.39
     burlap
    0.39
    聞き
    0.38
    Act Density 0.000%

    No Known Activations