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

    Neuronpedia

    INDEX
    Explanations

    vuoto and Pyhäjärvi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ars
    0.42
    ानगर
    0.42
    ार्
    0.42
    𝘢
    0.41
     Tübingen
    0.41
    ే
    0.41
    энер
    0.41
    ानों
    0.40
     Tup
    0.40
    घन
    0.40
    POSITIVE LOGITS
    ppo
    0.72
    hta
    0.62
    ppe
    0.59
    hti
    0.59
    hk
    0.58
    ud
    0.57
    itto
    0.56
    pper
    0.54
    ht
    0.53
    hte
    0.53
    Act Density 0.001%

    No Known Activations