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

    Neuronpedia

    INDEX
    Explanations

    foreign names and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     int
    0.53
     พ
    0.49
     З
    0.49
     ValueError
    0.45
    ความ
    0.45
     Z
    0.45
     One
    0.45
     capa
    0.44
    แบบ
    0.44
    0.44
    POSITIVE LOGITS
    oyeva
    0.79
    atthakath
    0.76
    arrerol
    0.75
    thorace
    0.72
    inerja
    0.72
    atthena
    0.72
    avkhat
    0.72
     yönetim
    0.72
    ilihan
    0.71
    orthin
    0.70
    Act Density 0.239%

    No Known Activations