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

    Neuronpedia

    INDEX
    Explanations

    variables and mathematical expressions indicating relationships or computations in a statistical context

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

    mathematical variables like x

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Kaynakça
    -0.38
     färg
    -0.32
    ambilan
    -0.31
     vedno
    -0.30
    Източници
    -0.30
     cantora
    -0.29
     Gesichts
    -0.29
     nahilalakip
    -0.29
    Sequence
    -0.29
     loob
    -0.29
    POSITIVE LOGITS
    ChildScrollView
    0.63
     absc
    0.59
    الدراسه
    0.58
     $_"
    0.58
    MemoryWarning
    0.54
    xmlWriter
    0.54
     getX
    0.53
    metas
    0.53
     queſta
    0.52
     xPos
    0.52
    Act Density 0.581%

    No Known Activations