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

    Neuronpedia

    INDEX
    Explanations

    local school, core domain, www web

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Optimal
    0.42
    лем
    0.41
     비밀
    0.40
    আলো
    0.40
    PEM
    0.39
    optimal
    0.39
    Optimization
    0.38
    gged
    0.38
    nią
    0.38
    ำ
    0.38
    POSITIVE LOGITS
    തേ
    0.50
     Kendrick
    0.43
     melan
    0.42
     থাকিতে
    0.42
     Nak
    0.41
     til
    0.41
     aidant
    0.41
     buds
    0.40
     Backend
    0.40
    ໂຕ
    0.40
    Act Density 0.001%

    No Known Activations