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

    Neuronpedia

    INDEX
    Explanations

    non-english characters and words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     it
    0.95
    quiries
    0.88
    ally
    0.87
    credibly
    0.85
    adequate
    0.81
    uous
    0.80
    he
    0.79
    ially
    0.79
    autiful
    0.78
    eworthy
    0.78
    POSITIVE LOGITS
    '
    0.93
    Es
    0.90
    Z
    0.88
    ক
    0.87
     dará
    0.86
    Ž
    0.86
     nécessaires
    0.86
     egyéb
    0.86
    El
    0.85
     Dé
    0.85
    Act Density 1.983%

    No Known Activations