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

    Neuronpedia

    INDEX
    Explanations

    GPT Series

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    waukee
    0.55
    人工智能
    0.47
    goài
    0.45
     आंख
    0.44
    ailed
    0.44
    erapeut
    0.44
    boor
    0.44
    nsics
    0.43
    skom
    0.43
    *
    0.42
    POSITIVE LOGITS
     eğ
    0.52
     metoda
    0.51
     maja
    0.49
     antara
    0.48
     proiz
    0.48
     punta
    0.48
     karar
    0.47
     Marta
    0.46
     ainult
    0.46
     nokta
    0.46
    Act Density 0.005%

    No Known Activations