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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to specific entities or titles

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

    the BOX console

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.47
    oarece
    -0.45
     Familienname
    -0.43
     kaynağından
    -0.42
     lentejuelas
    -0.41
    utilisons
    -0.40
    CheckBreak
    -0.40
    ungguh
    -0.40
    arthed
    -0.39
     pracovní
    -0.39
    POSITIVE LOGITS
    itself
    0.49
    myModal
    0.47
     Numerade
    0.44
    reality
    0.43
    WillAppear
    0.43
     Reality
    0.42
    Reality
    0.42
     Rela
    0.42
    TextAlign
    0.42
    modulation
    0.42
    Act Density 0.056%

    No Known Activations