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

    Neuronpedia

    INDEX
    Explanations

    perhaps I data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    age
    0.49
    ure
    0.48
    ama
    0.44
     चलन
    0.43
    ood
    0.42
    born
    0.42
    achi
    0.42
    ff
    0.42
    uting
    0.42
    icip
    0.41
    POSITIVE LOGITS
    INSERT
    0.51
     ByteArray
    0.50
    و
    0.49
    日报
    0.49
    수
    0.48
    ।--
    0.47
     লবণ
    0.47
     수
    0.47
    회
    0.46
    Baş
    0.45
    Act Density 0.027%

    No Known Activations