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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating certainty or assurance

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

    "Of course" or its translations

    np_acts-logits-general · gemini-2.0-flash

    of course, naturally, clearly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jScrollPane
    -0.58
     reportedly
    -0.54
    omitempty
    -0.51
    Bibliograf
    -0.50
    qrstuvwxyz
    -0.50
    どうやら
    -0.49
    either
    -0.49
     either
    -0.49
    mittag
    -0.49
    bunal
    -0.49
    POSITIVE LOGITS
    følgelig
    0.89
    verständlich
    0.85
     Natürlich
    0.84
    Natürlich
    0.83
    ürlich
    0.83
     ovviamente
    0.78
     course
    0.75
     natürlich
    0.75
    Конечно
    0.75
     ofc
    0.74
    Act Density 0.090%

    No Known Activations