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

    Neuronpedia

    INDEX
    Explanations

    ice bath

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deducting
    0.39
    Wend
    0.38
    )^{*}\
    0.37
     Phnom
    0.36
     लड़ने
    0.36
     কিশোর
    0.36
     YEAR
    0.35
    రా
    0.35
    DISTANCE
    0.35
    ienna
    0.35
    POSITIVE LOGITS
     bath
    1.23
     baths
    1.21
    Bath
    1.09
     Baths
    1.03
     Bath
    1.02
    bath
    1.02
    浴
    0.90
     bathe
    0.86
     BATH
    0.82
     baño
    0.76
    Act Density 0.015%

    No Known Activations