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

    Neuronpedia

    INDEX
    Explanations

    math, water, numbers, verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ることができます
    1.16
    ein
    1.14
    ை
    1.11
     불구하고
    1.10
    chinen
    1.06
    )}(
    1.04
    ান
    1.03
    لاف
    1.03
    কাতার
    1.02
    ️
    1.01
    POSITIVE LOGITS
     sigui
    1.07
     spic
    1.02
     instinct
    1.02
     Theme
    0.99
     esperienza
    0.99
     أساس
    0.97
     jurisdiction
    0.96
     Sanct
    0.96
     Estat
    0.95
    er
    0.95
    Act Density 0.045%

    No Known Activations