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

    Neuronpedia

    INDEX
    Explanations

    terms related to programming objects, methods, and data structures in a technical context

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

    class or item names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __(/*!
    -0.63
     lateinit
    -0.61
     ***!
    -0.60
     createState
    -0.60
     мәкал
    -0.59
     snippetHide
    -0.57
     كومونز
    -0.57
     jScrollPane
    -0.54
    WriteTagHelper
    -0.54
    Personendaten
    -0.51
    POSITIVE LOGITS
    transQ
    0.58
     Monfieur
    0.58
     Krakowie
    0.56
     nothwendig
    0.55
    findOneAndUpdate
    0.53
     desmotivaciones
    0.52
    expandindo
    0.50
     Atlántico
    0.50
     feroit
    0.50
    bindet
    0.49
    Act Density 0.596%

    No Known Activations