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

    Neuronpedia

    INDEX
    Explanations

    to arguments, legislation, find

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     paycheck
    0.43
     applauded
    0.41
     comedor
    0.40
     bustling
    0.40
     earnings
    0.40
     meadow
    0.39
     Guthrie
    0.39
     intento
    0.39
     yaad
    0.39
     grocery
    0.38
    POSITIVE LOGITS
     सूत्रों
    0.50
    rules
    0.40
     Tattoo
    0.40
    ogenerated
    0.40
    Polynomial
    0.38
    暾
    0.38
     Atomic
    0.38
     Equation
    0.38
     Fishes
    0.38
    करण
    0.38
    Act Density 0.001%

    No Known Activations