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

    Neuronpedia

    INDEX
    Explanations

    libraryattackgreatestdestinations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Deserial
    0.41
     unsupervised
    0.41
     využ
    0.41
     Charakter
    0.39
     coercive
    0.39
    ազմ
    0.38
     abuso
    0.37
     ಬಳ
    0.37
     दिखाने
    0.37
     supervis
    0.37
    POSITIVE LOGITS
    ็ก
    0.38
    త్ర
    0.38
    ﾅ
    0.37
    ortis
    0.36
    urnd
    0.36
    呢
    0.36
    銇
    0.35
    groovy
    0.35
    櫒
    0.35
    ন্ধে
    0.34
    Act Density 0.000%

    No Known Activations