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

    Neuronpedia

    INDEX
    Explanations

    end of turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    P
    0.81
    ً
    0.79
    ,
    0.79
    ́
    0.75
    (
    0.75
    <0xF0>
    0.69
    G
    0.69
    T
    0.68
    /
    0.67
    \
    0.66
    POSITIVE LOGITS
     今天
    1.30
     Seems
    1.28
    <unused1073>
    1.28
    亅
    1.27
     Și
    1.25
    <unused639>
    1.22
     Daunting
    1.20
     Tämä
    1.19
     Spacious
    1.19
     Despite
    1.19
    Act Density 3.147%

    No Known Activations