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

    Neuronpedia

    INDEX
    Explanations

    Kyle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     packages
    0.39
     vé
    0.39
    يدية
    0.38
     वे
    0.37
    枤
    0.37
     ভে
    0.37
    맞
    0.37
    idcar
    0.36
    ෑ
    0.36
    궂
    0.36
    POSITIVE LOGITS
    Wonder
    0.41
     Leukemia
    0.41
    Sun
    0.37
    University
    0.36
    Maximum
    0.36
    $-$,
    0.36
     Tilt
    0.36
    𝐻
    0.35
     Wonder
    0.35
    Un
    0.35
    Act Density 0.001%

    No Known Activations