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

    Neuronpedia

    INDEX
    Explanations

    this that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _hierarchy
    -0.07
    PrivateKey
    -0.06
    -util
    -0.06
    ail
    -0.06
    _bundle
    -0.06
    ekil
    -0.06
    .Destroy
    -0.06
    拓
    -0.06
    Opacity
    -0.06
    ุง
    -0.06
    POSITIVE LOGITS
     these
    0.08
    งเศ
    0.06
     BE
    0.06
    opause
    0.06
    ندا
    0.06
    事件
    0.06
     kê
    0.06
     гар
    0.06
     DES
    0.06
    났다
    0.06
    Act Density 0.060%

    No Known Activations