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

    Neuronpedia

    INDEX
    Explanations

    occurrences of punctuation and special characters in code-like syntax

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

    `assert(`, `do`, `)`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.73
    sizeCache
    -0.63
    oa̍t
    -0.58
     мәкал
    -0.57
     houſe
    -0.56
    Rohy
    -0.53
    хьтан
    -0.53
    HideFlags
    -0.52
     ✭✭
    -0.52
    RegistryLite
    -0.51
    POSITIVE LOGITS
     relationship
    0.42
    mapStateToProps
    0.41
    oulos
    0.41
     کمک
    0.40
     help
    0.40
     Connelly
    0.40
    таратура
    0.40
    berfläche
    0.40
    Lazy
    0.38
    看
    0.38
    Act Density 0.006%

    No Known Activations