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

    Neuronpedia

    INDEX
    Explanations

    a word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     också
    0.38
     ALSO
    0.37
     również
    0.37
     też
    0.36
     whose
    0.36
     onto
    0.35
     olds
    0.35
     existente
    0.35
     appareils
    0.35
     نیز
    0.34
    POSITIVE LOGITS
    cknowled
    0.86
    cknow
    0.73
    swering
    0.67
    ided
    0.60
    waiting
    0.59
    romatic
    0.52
    verages
    0.51
     few
    0.50
    rugula
    0.50
    ileen
    0.49
    Act Density 0.071%

    No Known Activations