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

    Neuronpedia

    INDEX
    Explanations

    actions and transitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     distort
    0.45
     pared
    0.40
     irrepar
    0.39
     Esqu
    0.38
    ulture
    0.38
     سکتے
    0.38
    cripts
    0.38
    zov
    0.38
    z
    0.38
     tumult
    0.38
    POSITIVE LOGITS
    ޕ
    0.45
     подарок
    0.44
    годно
    0.44
     rallying
    0.43
    ambahkan
    0.42
    рып
    0.40
    蠔
    0.40
    щению
    0.40
    رويج
    0.40
    㳖
    0.40
    Act Density 0.000%

    No Known Activations