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

    Neuronpedia

    INDEX
    Explanations

    words ending in -ological, -ational, -ual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sogenannte
    0.79
     sogenannten
    0.77
    quela
    0.70
    S
    0.70
    માં
    0.69
    كي
    0.69
     starken
    0.68
    U
    0.68
    いい
    0.68
    يل
    0.66
    POSITIVE LOGITS
    ity
    0.83
    ITY
    0.65
    )
    0.61
     exuber
    0.60
     misconduct
    0.60
    AND
    0.58
    0.54
     fervor
    0.54
    ized
    0.54
    .
    0.53
    Act Density 0.395%

    No Known Activations