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

    Neuronpedia

    INDEX
    Explanations

    cloud services and providers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اً
    1.45
    ように
    1.42
    ે
    1.35
    ന്ന
    1.29
     shortlist
    1.28
    сус
    1.25
     atlet
    1.25
    ndvi
    1.23
    contours
    1.22
     Polri
    1.21
    POSITIVE LOGITS
    ر
    1.91
    u
    1.75
    л
    1.70
    er
    1.66
    しかも
    1.65
    ০
    1.52
    THING
    1.43
    }$\
    1.41
    ยนต์
    1.41
    мся
    1.40
    Act Density 0.145%

    No Known Activations