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

    Neuronpedia

    INDEX
    Explanations

    references to unsolicited or promotional mail types, particularly spam

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

    unsolicited mail and subscriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     createSlice
    -0.54
    SPATH
    -0.50
    Tikang
    -0.50
     Vikipedi
    -0.45
    Diweddarwch
    -0.44
     ویکی‌پدی
    -0.44
    Rujuakan
    -0.42
    WriteTagHelper
    -0.42
     fVar
    -0.39
    eadilan
    -0.36
    POSITIVE LOGITS
     Wikiseite
    0.49
     CanadaChoose
    0.49
    InitVars
    0.46
    Personendaten
    0.46
    ohl
    0.44
    pexpr
    0.43
    omel
    0.42
     annoying
    0.42
    EndContext
    0.41
     roboc
    0.41
    Act Density 0.196%

    No Known Activations