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

    Neuronpedia

    INDEX
    Explanations

    then followed by comma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    所有
    1.23
     Rhiz
    1.20
    ਆਂ
    1.19
    和
    1.13
    Π
    1.13
     Tüm
    1.12
     和
    1.10
     সমস্ত
    1.10
     whanne
    1.10
    Ι
    1.10
    POSITIVE LOGITS
    ↵↵
    1.15
    et
    1.14
    ok
    1.06
    use
    1.06
    lease
    1.01
    on
    1.00
    ays
    1.00
    off
    0.98
    als
    0.97
    ','
    0.96
    Act Density 0.427%

    No Known Activations