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

    Neuronpedia

    INDEX
    Explanations

    programming-related imports and structure in code

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

    Code imports (Java, Kotlin, Javascript, Python)

    np_acts-logits-general · gemini-2.0-flash

    code imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.67
     تانيه
    -0.56
    parsedMessage
    -0.56
    RTLD
    -0.55
    astify
    -0.54
     Chwiliwch
    -0.54
     dil
    -0.52
    <unused58>
    -0.52
    <unused21>
    -0.52
    <unused6>
    -0.52
    POSITIVE LOGITS
     estekak
    0.46
     defaultstate
    0.40
     ModelExpression
    0.36
     Créez
    0.32
     témoignage
    0.31
     CanadaChoose
    0.31
     Normdatei
    0.30
     nouvel
    0.30
     rağmen
    0.29
    Conclusie
    0.29
    Act Density 0.063%

    No Known Activations