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

    Neuronpedia

    INDEX
    Explanations

    occurrences of empty strings in various contexts

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

    Empty strings

    np_acts-logits-general · gemini-2.0-flash

    code snippets and data definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ы
    -0.64
    ات
    -0.64
     أنها
    -0.59
     counter
    -0.59
    counter
    -0.58
    s
    -0.58
     tra
    -0.57
    es
    -0.57
    ges
    -0.57
    intero
    -0.56
    POSITIVE LOGITS
     ainfi
    0.89
     auffi
    0.81
     pleaſure
    0.78
    (""+
    0.77
    ",""
    0.74
    UnsafeEnabled
    0.74
     ""
    0.73
     quæ
    0.73
     الاطلاع
    0.72
    ="",
    0.72
    Act Density 0.158%

    No Known Activations