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

    Neuronpedia

    INDEX
    Explanations

    rule-based chatbots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dépour
    0.44
    itude
    0.40
     siy
    0.40
     Shane
    0.40
     monastic
    0.39
    tolerance
    0.39
    wearing
    0.39
     Manifest
    0.38
    ુંદર
    0.38
     metaphysical
    0.38
    POSITIVE LOGITS
     publics
    0.46
     februar
    0.45
     및
    0.44
    ৰ
    0.44
     confirms
    0.44
     của
    0.43
     기준으로
    0.43
     오후
    0.43
     福
    0.42
     ARE
    0.42
    Act Density 0.002%

    No Known Activations