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

    Neuronpedia

    INDEX
    Explanations

    city, visa, meal, trails, friend, day

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fizemos
    0.46
     float
    0.45
     tomto
    0.44
     killed
    0.44
     makes
    0.43
     dedo
    0.43
     AMPL
    0.43
     voted
    0.43
     ezzel
    0.42
     deplete
    0.42
    POSITIVE LOGITS
    lø
    0.53
    F
    0.48
    trab
    0.48
    im
    0.48
    임
    0.47
    इज
    0.46
    நே
    0.45
    イ
    0.45
    iczne
    0.45
    就业
    0.44
    Act Density 0.004%

    No Known Activations