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

    Neuronpedia

    INDEX
    Explanations

    Lists and code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nurse
    0.47
    可是
    0.46
     venta
    0.43
     sentire
    0.43
    ^{-}$
    0.42
     keyValue
    0.42
    🚠
    0.41
     পারে
    0.41
    那是
    0.41
     रुका
    0.40
    POSITIVE LOGITS
    з
    0.59
    휘
    0.47
    По
    0.46
    نت
    0.46
    О
    0.45
    O
    0.44
     prez
    0.44
    Lists
    0.44
    न
    0.44
    6
    0.43
    Act Density 0.003%

    No Known Activations