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

    Neuronpedia

    INDEX
    Explanations

    lubrication / lubuntu / lublin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     _{
    0.44
    روز
    0.44
     Never
    0.39
     Haci
    0.39
     ^{
    0.38
     hangat
    0.38
     Ble
    0.37
    ^*_{
    0.37
    日間
    0.37
     Operand
    0.37
    POSITIVE LOGITS
    Lub
    0.59
     lubric
    0.52
     Lub
    0.52
     lub
    0.52
    lub
    0.51
     lubricating
    0.51
     lubricants
    0.48
     lubrication
    0.46
    ufficient
    0.42
     Lubric
    0.42
    Act Density 0.002%

    No Known Activations