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

    Neuronpedia

    INDEX
    Explanations

    specific numerical or mathematical expressions and annotations

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

    /* symbol following words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.41
     bürger
    -0.40
    󠁣
    -0.40
     CIVIL
    -0.39
     schmerz
    -0.39
     충
    -0.38
     Popov
    -0.38
     civile
    -0.38
     COLL
    -0.38
    setColumn
    -0.38
    POSITIVE LOGITS
    awtextra
    0.64
    NameInMap
    0.54
     mergeFrom
    0.50
     دیکھیے
    0.49
     nahilalakip
    0.46
    addGap
    0.45
    tagext
    0.43
    bkz
    0.42
    AISSEE
    0.41
    ValueStyle
    0.40
    Act Density 0.671%

    No Known Activations