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

    Neuronpedia

    INDEX
    Explanations

    punctuation and conjunctions that indicate complex sentence structures

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

    descriptive adjectives or adverbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tazama
    -0.54
     NSCoder
    -0.54
     feroit
    -0.52
    LabelTagHelper
    -0.51
     typelib
    -0.50
    CppCodeGen
    -0.50
     desmotivaciones
    -0.48
    estacks
    -0.47
    GTCX
    -0.46
    Җ
    -0.45
    POSITIVE LOGITS
    Parcelize
    0.45
    istoitu
    0.44
     autorytatywna
    0.43
     painless
    0.40
     highly
    0.39
    TargetApi
    0.39
    ℗
    0.38
    isDisplayed
    0.37
     solvable
    0.37
    )}=
    0.37
    Act Density 0.021%

    No Known Activations