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

    Neuronpedia

    INDEX
    Explanations

    data, to, and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ($("#
    0.43
     सार्वजनिक
    0.42
     общественного
    0.42
    参考に
    0.42
    ProductRunnable
    0.41
     население
    0.41
     fungicides
    0.41
    घरों
    0.41
     जंगली
    0.41
    Ἥ
    0.41
    POSITIVE LOGITS
    sm
    0.40
     verbess
    0.38
     enhance
    0.38
    br
    0.37
    iet
    0.37
    improve
    0.37
    v
    0.37
     internal
    0.37
    ud
    0.37
    యోజ
    0.36
    Act Density 0.004%

    No Known Activations