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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    さまざまな
    0.91
    有效地
    0.79
     –,
    0.74
    ‒
    0.73
     العديد
    0.71
     Tuttavia
    0.70
    电子邮件
    0.70
     באמצעות
    0.69
    」（
    0.68
    하십시오
    0.67
    POSITIVE LOGITS
     đc
    1.19
     чтоб
    1.13
     perchè
    1.08
     cca
    1.05
     yg
    1.05
     наверное
    1.04
     piu
    1.02
    ってる
    1.00
     tambien
    0.99
     tengo
    0.98
    Act Density 0.041%

    No Known Activations