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

    Neuronpedia

    INDEX
    Explanations

    JSON decoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    po
    0.42
    çok
    0.40
    akai
    0.40
    ーズ
    0.38
    жнарод
    0.38
    °)
    0.38
     கொ
    0.38
    <unused367>
    0.37
     INSEE
    0.37
    aidl
    0.37
    POSITIVE LOGITS
     ony
    0.41
     Elev
    0.39
    របស់យើង
    0.39
     elicit
    0.37
     complimented
    0.37
    IManager
    0.37
    ек
    0.37
    ências
    0.36
    اح
    0.35
    бот
    0.35
    Act Density 0.012%

    No Known Activations