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

    Neuronpedia

    INDEX
    Explanations

    checking for or in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     checks
    1.57
     проверя
    1.52
     Checks
    1.46
     check
    1.46
     überprüfen
    1.44
     проверить
    1.43
     verifies
    1.41
    Check
    1.41
     checked
    1.39
    verify
    1.38
    POSITIVE LOGITS
     out
    1.21
    mate
    1.07
    outs
    0.98
    sam
    0.95
    lists
    0.95
     subjug
    0.93
    sa
    0.92
     గ్ర
    0.92
    points
    0.89
    cordova
    0.89
    Act Density 0.055%

    No Known Activations