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

    Neuronpedia

    INDEX
    Explanations

    accessing and processing information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ́c
    0.42
    🇽
    0.42
    INCLUDE
    0.41
    كو
    0.40
    իկ
    0.40
    ̣c
    0.39
    ۶
    0.39
     calculateur
    0.39
    gameState
    0.38
     متحده
    0.38
    POSITIVE LOGITS
    '
    0.47
     D
    0.42
     N
    0.42
     J
    0.39
     A
    0.38
    f
    0.38
     Down
    0.37
     Year
    0.37
     Y
    0.36
     H
    0.36
    Act Density 0.007%

    No Known Activations