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

    Neuronpedia

    INDEX
    Explanations

    foreign language, numbers, and programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    de
    0.59
    y
    0.56
    apons
    0.50
    roje
    0.49
    was
    0.48
     yì
    0.47
    minimum
    0.46
    ق
    0.46
    sterne
    0.46
    tsp
    0.46
    POSITIVE LOGITS
     Gloves
    0.49
     chords
    0.49
     Tochter
    0.48
     sfondo
    0.44
     Skull
    0.44
     teclas
    0.44
     Glove
    0.43
     листь
    0.43
     Уда
    0.43
     เหล
    0.42
    Act Density 0.000%

    No Known Activations