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

    Neuronpedia

    INDEX
    Explanations

    programming language keywords and libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RELATIVA
    0.43
    Despatx
    0.42
    ASCADE
    0.41
    GTUIKit
    0.41
    𒊬
    0.41
    utherland
    0.41
    蚤
    0.40
    vaegir
    0.40
    หมือน
    0.39
    ylmethylsulfanyl
    0.39
    POSITIVE LOGITS
     (
    0.48
     a
    0.45
     in
    0.44
     v
    0.44
     lib
    0.44
     the
    0.43
     from
    0.42
     options
    0.41
     countries
    0.40
     t
    0.39
    Act Density 0.179%

    No Known Activations