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

    Neuronpedia

    INDEX
    Explanations

    recent changes or observations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    0.98
    ،
    0.82
    :
    0.80
     curve
    0.73
     '
    0.72
     off
    0.72
     counsel
    0.70
    ovice
    0.69
    ',
    0.69
    arch
    0.69
    POSITIVE LOGITS
     ạ
    1.46
    ㄺ
    1.32
    ንዱ
    1.25
    בל
    1.21
     circulación
    1.21
     सेल्स
    1.21
     gdyż
    1.20
    いております
    1.18
    <unused220>
    1.16
    getBase
    1.16
    Act Density 0.182%

    No Known Activations