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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks or semicolons in code

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

    start of turn user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.60
    abases
    -0.50
    endpush
    -0.50
     وتسجيلات
    -0.49
    AndroidJUnit
    -0.47
    styleType
    -0.47
     незавершена
    -0.46
    riors
    -0.46
     gendar
    -0.46
    quiao
    -0.44
    POSITIVE LOGITS
     urme
    0.43
     HttpNotFound
    0.39
     Streifen
    0.37
    JsonIgnore
    0.36
    ształ
    0.36
    0.36
    plona
    0.35
    AccessorTable
    0.35
    QMetaType
    0.34
     praw
    0.34
    Act Density 0.000%

    No Known Activations