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

    Neuronpedia

    INDEX
    Explanations

    git branches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StillWater
    0.46
    複雜
    0.42
    ulières
    0.41
    estes
    0.40
    复杂
    0.39
    糁
    0.39
    十一章
    0.39
    枇
    0.39
    hôpital
    0.38
     année
    0.38
    POSITIVE LOGITS
     вашего
    0.36
     መ
    0.36
    राष्ट
    0.35
     zawier
    0.35
     Wagner
    0.35
     quotidienne
    0.35
    ++;//
    0.35
     containing
    0.34
     اجيب
    0.34
     ole
    0.34
    Act Density 0.000%

    No Known Activations