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

    Neuronpedia

    INDEX
    Explanations

    do, does, did

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     мень
    0.50
     menos
    0.49
     менее
    0.49
     moins
    0.47
     LESS
    0.47
     SAI
    0.46
     меньше
    0.45
    ursa
    0.44
     Less
    0.42
     lesser
    0.42
    POSITIVE LOGITS
     happen
    0.44
     occur
    0.42
     directions
    0.41
     nothing
    0.41
    ゥム
    0.40
     ocorrer
    0.38
     கொண்டார்
    0.38
     llegue
    0.37
     nimic
    0.37
    莯
    0.37
    Act Density 0.000%

    No Known Activations