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

    Neuronpedia

    INDEX
    Explanations

    snippets of computer code

    oai_token-act-pair · gemini-2.0-flash

    prefixes or patterns in strings

    np_token-act-pair-logits · gpt-4o-mini

    Code and error messages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    __(/*!
    -0.87
    ">//
    -0.79
    Havolalar
    -0.79
     kaarangay
    -0.78
     فريبيس
    -0.77
    Хьажоргаш
    -0.75
    MLLoader
    -0.73
     ModelExpression
    -0.72
     برانيه
    -0.72
     للاسماء
    -0.72
    POSITIVE LOGITS
     des
    0.52
     pro
    0.51
    jaan
    0.48
    的态度
    0.48
     <
    0.46
     Pro
    0.45
    8
    0.44
    hele
    0.44
    teryx
    0.44
     Bre
    0.43
    Act Density 0.996%

    No Known Activations