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

    Neuronpedia

    INDEX
    Explanations

    label or self

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     caption
    0.50
    caption
    0.48
    Description
    0.43
     captions
    0.43
    Caption
    0.42
     descripción
    0.42
     descrição
    0.41
     Caption
    0.40
     description
    0.40
     Dise
    0.39
    POSITIVE LOGITS
    𒈦
    0.41
    way
    0.40
    abaya
    0.38
    ចំ
    0.38
    ខាង
    0.38
    ज्यो
    0.38
    abhav
    0.37
     format
    0.37
     ෆ
    0.37
     typology
    0.36
    Act Density 0.000%

    No Known Activations