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

    Neuronpedia

    INDEX
    Explanations

    function declarations and variable assignments in programming code

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

    academic or programming context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    URLException
    -0.63
    neſs
    -0.57
     houſe
    -0.52
     itſelf
    -0.52
    ſelf
    -0.50
     ſta
    -0.49
    Diweddarwch
    -0.49
     Houſe
    -0.48
     pleaſure
    -0.46
    şam
    -0.45
    POSITIVE LOGITS
    anInt
    0.53
    Obfuscated
    0.52
    NameInMap
    0.48
    reactivex
    0.46
     otomatig
    0.45
     contacter
    0.44
    はじめに
    0.43
     reputación
    0.43
    mobileqq
    0.43
    vivencia
    0.41
    Act Density 0.007%

    No Known Activations