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

    Neuronpedia

    INDEX
    Explanations

    indicates varying definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ли
    0.50
    Anthrop
    0.49
    во
    0.43
     Anthropology
    0.42
    DO
    0.42
    Sandbox
    0.41
     DO
    0.41
     installment
    0.41
    сима
    0.41
     instalment
    0.41
    POSITIVE LOGITS
     वी
    0.44
     reine
    0.42
     sac
    0.40
     সম্মুখ
    0.40
    同樣
    0.39
    nocześnie
    0.39
    復
    0.39
     scrollTop
    0.38
    靜
    0.38
     incre
    0.38
    Act Density 0.000%

    No Known Activations