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

    Neuronpedia

    INDEX
    Explanations

    error messages and code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     निराश
    0.44
    distanceArray
    0.42
     kojima
    0.41
     коды
    0.40
     negativas
    0.40
    اونلو
    0.39
     السالب
    0.39
     negatif
    0.39
     درمان
    0.39
     реаги
    0.38
    POSITIVE LOGITS
     causality
    0.44
     CAE
    0.42
     causa
    0.42
     cause
    0.41
     causal
    0.41
    Caught
    0.40
    cau
    0.40
     caused
    0.39
     maladies
    0.39
     causative
    0.38
    Act Density 0.058%

    No Known Activations