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

    Neuronpedia

    INDEX
    Explanations

    Greek and Russian word endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XEL
    0.40
     moy
    0.39
    ESH
    0.38
    Jeremy
    0.38
    xel
    0.37
    мо
    0.36
    锁
    0.36
    اتر
    0.36
    濃
    0.35
    요일
    0.35
    POSITIVE LOGITS
    ଥି
    0.42
    usa
    0.40
    requis
    0.39
    México
    0.39
     tagging
    0.37
    OSA
    0.36
     സാ
    0.36
    sak
    0.36
    ଛି
    0.36
     Mediator
    0.36
    Act Density 0.002%

    No Known Activations