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

    Neuronpedia

    INDEX
    Explanations

    A leading word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kind
    0.83
     sorts
    0.83
     kinda
    0.79
     sort
    0.76
    kind
    0.73
     çeşitli
    0.72
     already
    0.72
     bastante
    0.71
     Already
    0.70
     soort
    0.70
    POSITIVE LOGITS
    cknowled
    1.47
    cknow
    1.31
    swering
    1.28
    nya
    1.20
    oretically
    1.18
    pesar
    1.15
    voorbeeld
    1.12
     hallmark
    1.12
    ためには
    1.11
    rugula
    1.10
    Act Density 0.235%

    No Known Activations