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

    Neuronpedia

    INDEX
    Explanations

    melting ice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Art
    0.43
    fox
    0.42
     sets
    0.41
     forte
    0.39
    fort
    0.38
    fre
    0.38
    Andrea
    0.38
     art
    0.37
    Autor
    0.37
     fortified
    0.37
    POSITIVE LOGITS
     مدار
    0.39
     MainPage
    0.39
    阻塞
    0.38
    નારા
    0.37
     Neighbourhood
    0.36
    _->
    0.36
     GameOver
    0.36
     Meals
    0.36
     Broadband
    0.36
    してきた
    0.35
    Act Density 0.002%

    No Known Activations