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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comprehension or understanding

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

    understanding or lack thereof

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    깐
    -0.51
     consommate
    -0.44
     kecelakaan
    -0.41
    Linki
    -0.41
     egz
    -0.40
     Otras
    -0.39
     aveug
    -0.39
     ब्रेकडाउन
    -0.39
     agência
    -0.39
     mutiara
    -0.38
    POSITIVE LOGITS
     understood
    1.75
    understood
    1.54
    Understood
    1.23
     misunderstood
    0.85
    stood
    0.84
     comprehended
    0.78
     verstanden
    0.76
     defined
    0.71
     Defined
    0.71
     Knew
    0.66
    Act Density 0.004%

    No Known Activations