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

    Neuronpedia

    INDEX
    Explanations

    Breakdown regions geographic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ქვთ
    0.41
     neural
    0.40
     زیاد
    0.38
     $(-
    0.38
     Brazil
    0.38
     irradi
    0.37
    袒
    0.37
     unconsciously
    0.37
     xúc
    0.37
     kı
    0.37
    POSITIVE LOGITS
     szyb
    0.43
    ío
    0.41
    courses
    0.41
     definitiv
    0.41
     फटाफट
    0.40
    Fourth
    0.40
    ]_{\
    0.39
    Rapid
    0.39
    迅速
    0.39
    驟
    0.39
    Act Density 0.000%

    No Known Activations