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

    Neuronpedia

    INDEX
    Explanations

    Extensions, residential, minimums

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    whose
    0.41
    known
    0.40
    provides
    0.40
    entgen
    0.40
     মহাশয়ের
    0.39
     coloro
    0.39
    州市
    0.39
    と呼ばれる
    0.38
    ߋ
    0.37
    namely
    0.37
    POSITIVE LOGITS
     якщо
    0.46
    で
    0.45
     కానీ
    0.45
     AND
    0.44
     +
    0.44
     if
    0.42
    만
    0.42
     если
    0.42
     برای
    0.42
     değil
    0.41
    Act Density 0.034%

    No Known Activations