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

    Neuronpedia

    INDEX
    Explanations

    sequences or patterns of symbols and special characters

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

    code and non-english words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     geſch
    -0.89
    parsedMessage
    -0.89
     $_"
    -0.84
    iſen
    -0.82
     $_(
    -0.82
     houſe
    -0.81
    ſcher
    -0.81
    ſſung
    -0.79
    iſche
    -0.79
     Weiſe
    -0.78
    POSITIVE LOGITS
     AssemblyCompany
    0.39
    import
    0.35
     +=
    0.35
     prostřed
    0.35
     måte
    0.34
     아니라
    0.33
    WithFormat
    0.33
    return
    0.33
    WriteLiteral
    0.32
     “
    0.32
    Act Density 0.010%

    No Known Activations