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

    Neuronpedia

    INDEX
    Explanations

    Nevada and Las Vegas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ów
    0.59
    ną
    0.58
    ian
    0.56
    kiewicz
    0.55
    noz
    0.54
    ing
    0.54
     आउट
    0.53
    àu
    0.52
     India
    0.52
    ral
    0.51
    POSITIVE LOGITS
    وف
    0.59
     pc
    0.58
     manometer
    0.58
    चणी
    0.55
     UEFI
    0.55
     Reno
    0.55
     condom
    0.54
    РО
    0.54
    毉
    0.54
    체의
    0.54
    Act Density 0.007%

    No Known Activations