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

    Neuronpedia

    INDEX
    Explanations

    currency amounts or numerical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     réglement
    0.33
     routinely
    0.33
     venons
    0.33
    и
    0.33
    бычно
    0.33
     venturing
    0.32
     પછી
    0.32
     vías
    0.32
    ורך
    0.32
    rogenic
    0.31
    POSITIVE LOGITS
     \
    0.40
    an
    0.39
    k
    0.37
    0.36
     $
    0.35
    n
    0.35
    y
    0.34
     Math
    0.34
     The
    0.34
     You
    0.33
    Act Density 0.126%

    No Known Activations