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

    Neuronpedia

    INDEX
    Explanations

    data and related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deren
    0.20
    នូវ
    0.20
     বলিল
    0.20
     testAvg
    0.20
    itled
    0.20
    нению
    0.20
     خپل
    0.19
     اپنے
    0.19
     आफ्नो
    0.19
     तबाद
    0.19
    POSITIVE LOGITS
     they
    0.52
     we
    0.49
     offered
    0.43
     that
    0.40
     που
    0.40
     used
    0.39
     involved
    0.38
    that
    0.38
     you
    0.38
     taken
    0.36
    Act Density 0.375%

    No Known Activations