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

    Neuronpedia

    INDEX
    Explanations

    informal language and expressions commonly used in casual conversation

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

    scientific notation and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tec
    -0.42
    Tec
    -0.39
    ToProps
    -0.35
    fVar
    -0.35
     defender
    -0.35
     buyer
    -0.35
     olor
    -0.35
    balleur
    -0.35
    MOTION
    -0.34
     buyers
    -0.34
    POSITIVE LOGITS
    IsMutable
    0.64
    featureID
    0.58
     AssemblyCompany
    0.55
    MigrationBuilder
    0.51
     مشين
    0.49
     dezelve
    0.48
     resourceCulture
    0.48
    ActionCreators
    0.48
    IndentedString
    0.48
    fjspx
    0.48
    Act Density 0.574%

    No Known Activations