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

    Neuronpedia

    INDEX
    Explanations

    pasta water seasoning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    溆
    0.45
    𝓪
    0.44
    ניים
    0.43
     שני
    0.42
    Можно
    0.42
    प्ताहिक
    0.41
    醾
    0.41
    AGMENT
    0.40
     combina
    0.40
    発表
    0.40
    POSITIVE LOGITS
     ofthe
    0.42
     hump
    0.42
     douche
    0.41
     tiềm
    0.40
     sweat
    0.40
     taxes
    0.39
     of
    0.39
    of
    0.38
    dau
    0.38
    িশালী
    0.37
    Act Density 0.016%

    No Known Activations