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

    Neuronpedia

    INDEX
    Explanations

    Single-acting steam engine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ip
    1.02
    ں
    1.00
    idity
    0.99
    ment
    0.96
     protect
    0.93
    ه‌
    0.89
    ه‌ای
    0.88
    "));
    0.88
     confirm
    0.88
    et
    0.87
    POSITIVE LOGITS
    ер
    1.02
     algu
    1.00
     fác
    1.00
     festivities
    0.99
    𝒐
    0.97
    OUND
    0.92
    OUG
    0.92
    AKES
    0.91
    ONA
    0.89
     álgebra
    0.89
    Act Density 0.001%

    No Known Activations