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

    Neuronpedia

    INDEX
    Explanations

    water always finds its level

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    訒
    0.39
     डाला
    0.38
    acil
    0.37
    詞
    0.37
    ofo
    0.36
    oleans
    0.36
    arse
    0.36
    分手
    0.36
    issements
    0.35
     ఆల
    0.35
    POSITIVE LOGITS
    Pig
    0.39
    ZER
    0.38
    앞
    0.38
     upbeat
    0.37
     carefree
    0.37
    Dik
    0.37
     Tiến
    0.37
    ުގައި
    0.36
    값
    0.36
     countertop
    0.36
    Act Density 0.001%

    No Known Activations