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

    Neuronpedia

    INDEX
    Explanations

    financial risk warnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    竇
    0.38
     ऑर्गेनिक
    0.38
    乨
    0.36
     PKC
    0.36
     pasada
    0.35
     জৈ
    0.35
    落ち着
    0.35
    下が
    0.35
    在这
    0.35
    MediaType
    0.35
    POSITIVE LOGITS
    ygon
    0.38
     Exhibits
    0.36
     ***
    0.35
     просмотра
    0.35
     vanqu
    0.35
    checks
    0.34
    video
    0.34
    verify
    0.34
     tagReport
    0.33
     irreplaceable
    0.33
    Act Density 0.002%

    No Known Activations