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

    Neuronpedia

    INDEX
    Explanations

    occurrences of parentheses

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

    code delimiters and parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enfans
    -0.45
    ekš
    -0.40
    adaptiveStyles
    -0.39
    <bos>
    -0.39
    </u>
    -0.39
     approach
    -0.38
    hip
    -0.38
    mtable
    -0.38
     ActionBar
    -0.35
    Kne
    -0.35
    POSITIVE LOGITS
     nahilalakip
    0.69
     ((
    0.65
    Personendaten
    0.60
    amaño
    0.56
    fjspx
    0.56
     ((((
    0.50
    joven
    0.48
     الحره
    0.47
    WarningLevel
    0.47
     voldoende
    0.46
    Act Density 0.005%

    No Known Activations