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

    Neuronpedia

    INDEX
    Explanations

    expressions of doubt or uncertainty in communication

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

    speculation and possibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Danemark
    -0.42
    wußt
    -0.41
     Küsten
    -0.41
    ことにしました
    -0.41
    awtextra
    -0.41
    KommentareTeilen
    -0.40
     desafíos
    -0.39
    わけです
    -0.39
     Chaves
    -0.38
     surla
    -0.38
    POSITIVE LOGITS
     disambiguazione
    0.56
    addPreferredGap
    0.55
    DllImport
    0.51
     PhpStorm
    0.43
     GIPHY
    0.43
     but
    0.43
    ropathy
    0.41
     superstition
    0.41
    UserScript
    0.41
    ApiProperty
    0.40
    Act Density 0.044%

    No Known Activations