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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and symbols related to functions and variables

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

    Text after a dollar sign, often math related

    np_acts-logits-general · gemini-2.0-flash

    mathematical symbols and greek letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.62
    jupiter
    -0.57
     دیکھیے
    -0.56
    PreferredItem
    -0.52
     fiche
    -0.51
    FailureListener
    -0.49
    afficheront
    -0.49
     velkommen
    -0.48
    spesies
    -0.48
    MessageOf
    -0.48
    POSITIVE LOGITS
     Abp
    0.70
     nahilalakip
    0.62
     CSD
    0.61
     EconPapers
    0.61
    |$
    0.60
     ProtoMessage
    0.59
    annica
    0.58
    endgroup
    0.58
    docs
    0.57
     Lino
    0.56
    Act Density 0.231%

    No Known Activations