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

    Neuronpedia

    INDEX
    Explanations

    continue if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tin
    0.47
    Hawaii
    0.45
    Issledovatel
    0.44
     gewährle
    0.43
    Tran
    0.43
    Tile
    0.43
    Hydrochloride
    0.43
    Tint
    0.42
    ieszcz
    0.42
    ocrates
    0.42
    POSITIVE LOGITS
    值
    0.47
    金額
    0.46
     Cu
    0.46
     entrepreneur
    0.45
    新
    0.44
    ouk
    0.44
     Wau
    0.44
    分數
    0.44
    都
    0.44
    原因
    0.43
    Act Density 0.002%

    No Known Activations