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

    Neuronpedia

    INDEX
    Explanations

    code snippets or references to programming functions

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

    appear immediately

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oprot
    -0.56
     Taktlose
    -0.53
     actionMode
    -0.47
    setVerticalGroup
    -0.45
     flexível
    -0.45
     perdagangan
    -0.43
    ragalactic
    -0.43
     EconPapers
    -0.43
     sesama
    -0.43
     typelib
    -0.42
    POSITIVE LOGITS
    Bakgrunnsstoff
    0.39
    protoimpl
    0.37
     مشين
    0.37
     Salta
    0.36
    hates
    0.36
    Externé
    0.35
    Abp
    0.35
    RefNanny
    0.35
     pseud
    0.35
     wash
    0.34
    Act Density 0.023%

    No Known Activations