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

    Neuronpedia

    INDEX
    Explanations

    a function or model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     जरूरत
    0.55
    性和
    0.55
    和小
    0.51
    hetam
    0.51
    bestroute
    0.50
     тільки
    0.48
     અમા
    0.48
    ्रेट
    0.48
     ו
    0.48
    度和
    0.48
    POSITIVE LOGITS
     which
    0.59
     equipment
    0.53
    0.52
     car
    0.50
     ion
    0.48
     whereby
    0.48
     waarbij
    0.48
     wherein
    0.48
     waarmee
    0.47
     dvs
    0.47
    Act Density 0.002%

    No Known Activations