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

    Neuronpedia

    INDEX
    Explanations

    generate creative content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     besondere
    0.54
     besonderen
    0.52
     besonders
    0.51
     др
    0.51
     szczególnie
    0.49
    一定的
    0.49
    较大的
    0.49
     curious
    0.47
     terutama
    0.47
     열심히
    0.47
    POSITIVE LOGITS
     dozens
    0.99
     entire
    0.95
     literalmente
    0.93
     literally
    0.92
     decenas
    0.81
    literally
    0.80
     hundreds
    0.79
     दर्जन
    0.77
     perfectly
    0.77
     Literally
    0.76
    Act Density 0.047%

    No Known Activations