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

    Neuronpedia

    INDEX
    Explanations

    positive outlook

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iziert
    0.81
    Rescue
    0.80
     अनुरोध
    0.78
     مهمه
    0.76
     Complexity
    0.75
    Limitations
    0.74
     perfetto
    0.74
    óricos
    0.72
    ৩২
    0.72
    报错
    0.71
    POSITIVE LOGITS
     omen
    1.46
     news
    1.45
     outcomes
    1.42
     prognosis
    1.42
     luck
    1.36
     vibes
    1.33
     outcome
    1.29
     deeds
    1.28
     reputation
    1.28
     prospects
    1.27
    Act Density 0.216%

    No Known Activations