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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     machining
    -0.07
    rin
    -0.06
    機能
    -0.06
    "D
    -0.06
     düny
    -0.06
    的小
    -0.06
    _likes
    -0.06
     PID
    -0.06
     wrongly
    -0.06
     національ
    -0.06
    POSITIVE LOGITS
    credited
    0.06
    newValue
    0.06
    사이트
    0.06
     часов
    0.06
    ですが
    0.06
     pearl
    0.06
     twentieth
    0.06
    zę
    0.06
    nesota
    0.06
    ンディ
    0.06
    Act Density 0.031%

    No Known Activations