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

    Neuronpedia

    INDEX
    Explanations

    able to perform actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     быть
    1.09
     Becoming
    1.07
     être
    1.07
     blive
    1.03
     Being
    1.00
     deviennent
    1.00
    被人
    0.98
     Become
    0.97
     become
    0.97
     essere
    0.94
    POSITIVE LOGITS
     quantitatively
    0.92
     unambiguously
    0.90
     comprehensively
    0.90
     rapidly
    0.89
     extensively
    0.83
     significantly
    0.80
     clearly
    0.76
     thoroughly
    0.75
     convincingly
    0.72
     quickly
    0.72
    Act Density 0.011%

    No Known Activations