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

    Neuronpedia

    INDEX
    Explanations

    symbolizes or interpreted states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     тренер
    0.47
     peau
    0.44
    勹
    0.42
     поверх
    0.41
     моги
    0.41
    推广
    0.41
     groupBy
    0.41
    льном
    0.41
     numOf
    0.40
    testers
    0.40
    POSITIVE LOGITS
     focus
    0.47
     persisted
    0.43
     immediately
    0.42
     persistence
    0.42
     $
    0.41
     opened
    0.41
     O
    0.39
     never
    0.39
     Focus
    0.38
    $
    0.38
    Act Density 0.000%

    No Known Activations