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

    Neuronpedia

    INDEX
    Explanations

    references to data, files, or clickable links related to statistics or information

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

    Click here

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eventdata
    -0.38
    __':
    -0.36
     felicidade
    -0.36
     Gegenteil
    -0.36
     paisagem
    -0.36
     său
    -0.36
     otomatig
    -0.35
     Gedanke
    -0.35
     solches
    -0.35
     publicitaires
    -0.34
    POSITIVE LOGITS
    Bears
    0.60
    assorted
    0.57
     Arth
    0.57
    zahn
    0.57
    0.56
     Archangel
    0.56
    sohn
    0.55
     Acre
    0.55
    сток
    0.53
    Bear
    0.52
    Act Density 0.991%

    No Known Activations