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

    Neuronpedia

    INDEX
    Explanations

    Pod related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Unser
    0.46
    삼성
    0.45
    CBS
    0.44
    Cookies
    0.42
    Бар
    0.42
     Vogue
    0.41
    伱
    0.41
    dokka
    0.41
    ]";
    0.41
     городских
    0.41
    POSITIVE LOGITS
     pod
    0.48
     pods
    0.42
    pod
    0.40
     caste
    0.39
     پل
    0.38
     ort
    0.38
     jet
    0.37
     mangrove
    0.37
     polymorphism
    0.37
     compaction
    0.37
    Act Density 0.001%

    No Known Activations