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

    Neuronpedia

    INDEX
    Explanations

    designed for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     modernization
    0.49
     وی
    0.49
     antigos
    0.48
    ში
    0.47
     ඔබට
    0.46
    osť
    0.46
    ید
    0.46
    iciência
    0.46
    atud
    0.46
     dalamnya
    0.45
    POSITIVE LOGITS
     Alice
    0.46
     Mixtures
    0.46
     Gastro
    0.43
     Prose
    0.42
     Confusion
    0.42
    嵐
    0.42
    Alice
    0.42
     Thumb
    0.41
     Faker
    0.41
    var
    0.41
    Act Density 0.001%

    No Known Activations