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

    Neuronpedia

    INDEX
    Explanations

    specific numeric values and programming-related terms in code or technical documentation

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

    Numbers followed by specific punctuation or characters

    np_acts-logits-general · gemini-2.0-flash

    Timestamp and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تقاوى
    -0.82
    EDEFAULT
    -0.76
    delwed
    -0.74
    SequentialGroup
    -0.69
     Chwiliwch
    -0.69
    uxxxx
    -0.68
     disambiguazione
    -0.67
    EndContext
    -0.67
    AddTagHelper
    -0.67
    migrationBuilder
    -0.66
    POSITIVE LOGITS
     खिला
    0.36
    Indent
    0.36
     Mannes
    0.34
    Signin
    0.34
     Giants
    0.33
     feeling
    0.33
    getPoint
    0.33
     Larson
    0.32
    Player
    0.32
     eman
    0.32
    Act Density 1.321%

    No Known Activations