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

    Neuronpedia

    INDEX
    Explanations

    breakdown of explanations or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    6
    0.55
    \*
    0.53
     виду
    0.52
    /
    0.50
    3
    0.49
    Name
    0.48
    undle
    0.48
    *
    0.48
     &
    0.47
    \
    0.47
    POSITIVE LOGITS
    धनों
    0.57
     கெல்வின்
    0.52
     culinary
    0.50
     महत्
    0.48
    天気
    0.48
     Jehova
    0.46
     getWeather
    0.46
    ப்படுவத
    0.46
     cuddling
    0.46
     drinking
    0.46
    Act Density 0.000%

    No Known Activations