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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the importance or emphasis of information being discussed

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

    introducing stated facts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    webElementXpaths
    -0.49
    SourceChecksum
    -0.42
    ぞ
    -0.39
     inva
    -0.39
    libft
    -0.38
     خم
    -0.36
     WT
    -0.36
     เข
    -0.36
     Wolf
    -0.35
    产
    -0.35
    POSITIVE LOGITS
     sumpay
    0.65
    Напомним
    0.64
    помним
    0.55
    migrationBuilder
    0.54
    IsMutable
    0.50
     erwäh
    0.50
    Revenir
    0.50
     blessés
    0.46
    bootstrapcdn
    0.45
     ricordare
    0.45
    Act Density 0.053%

    No Known Activations