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

    Neuronpedia

    INDEX
    Explanations

    special characters and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    स्टेबल
    0.52
     बबल
    0.45
    𒂠
    0.45
    牖
    0.45
     fibrils
    0.44
    Stabilise
    0.44
    केमॉन
    0.43
    ናል
    0.43
    Strafpunkte
    0.42
    ंपूर्
    0.42
    POSITIVE LOGITS
    0.49
     and
    0.45
     RF
    0.44
     Frontier
    0.40
     ->
    0.39
     Acc
    0.38
     (
    0.38
     \
    0.38
     AB
    0.38
    _
    0.38
    Act Density 0.039%

    No Known Activations