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

    Neuronpedia

    INDEX
    Explanations

    code-related syntax and structure in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    property assignments or values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PreferredItem
    -0.48
     autorytatywna
    -0.47
    parsedMessage
    -0.45
     Italijani
    -0.43
     Италијани
    -0.42
     Roskov
    -0.41
    rungsseite
    -0.41
    ResumeLayout
    -0.39
     المعيارى
    -0.39
    цезда
    -0.38
    POSITIVE LOGITS
     bench
    0.49
    findpost
    0.46
    жели
    0.45
     border
    0.45
    IntoConstraints
    0.43
     Scrip
    0.42
    ValueStyle
    0.42
     whine
    0.41
     fringe
    0.41
     Laver
    0.41
    Act Density 0.051%

    No Known Activations