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

    Neuronpedia

    INDEX
    Explanations

    frequency of specific terms related to experimental results

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

    numbers and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    majánló
    -0.80
     IBOutlet
    -0.77
     مرئيه
    -0.77
     autorytatywna
    -0.76
     kasarigan
    -0.73
    ſchaft
    -0.72
     $_(
    -0.71
    KommentareTeilen
    -0.71
    IBOutlet
    -0.71
    iſen
    -0.71
    POSITIVE LOGITS
    новништво
    0.32
    resave
    0.30
     rius
    0.26
     faible
    0.25
     Considering
    0.24
    ,
    0.24
     frecu
    0.24
     pourtant
    0.23
    模拟
    0.23
     successo
    0.23
    Act Density 0.090%

    No Known Activations