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

    Neuronpedia

    INDEX
    Explanations

    being tall

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    約
    0.45
    ５
    0.45
    ο
    0.45
    これらの
    0.45
    0.44
    ９
    0.43
    学者
    0.42
    μένες
    0.42
     extravagant
    0.41
     irregularly
    0.41
    POSITIVE LOGITS
    că
    0.48
     tío
    0.47
     chas
    0.43
     choć
    0.42
    osław
    0.41
    unoscut
    0.40
     Methodist
    0.40
     कै
    0.40
     disinterested
    0.39
     maid
    0.39
    Act Density 0.010%

    No Known Activations