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

    Neuronpedia

    INDEX
    Explanations

    list items and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     непосредственно
    0.53
    attiyam
    0.50
    惊讶
    0.49
    ettiin
    0.46
    ﯼ
    0.45
     करण
    0.44
     Carne
    0.44
    izioni
    0.43
    akkhati
    0.43
     بسیار
    0.42
    POSITIVE LOGITS
     each
    0.46
     warehouses
    0.41
    테
    0.40
     coffee
    0.40
     aging
    0.39
     đô
    0.39
     tidy
    0.39
     sum
    0.38
     ,,
    0.38
     weave
    0.37
    Act Density 0.000%

    No Known Activations