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

    Neuronpedia

    INDEX
    Explanations

    data=!3m1!4b1!4m6

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সরঞ্জাম
    0.37
    츨
    0.34
     rasa
    0.34
    SPE
    0.33
     slides
    0.33
     slight
    0.33
    waża
    0.33
    OPA
    0.32
     SPE
    0.32
    tsp
    0.32
    POSITIVE LOGITS
     Kamane
    0.45
    Longitude
    0.43
     Joaquín
    0.42
    ━━━━━━━━
    0.42
    Biden
    0.42
    ս
    0.41
     pilgrimage
    0.41
     Amor
    0.40
    ahin
    0.39
    Roxy
    0.39
    Act Density 0.003%

    No Known Activations