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

    Neuronpedia

    INDEX
    Explanations

    German language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     correction
    -0.07
    izons
    -0.07
     Setter
    -0.07
    耧
    -0.07
    Manufacturer
    -0.07
     flowing
    -0.07
    쉼
    -0.06
    Ether
    -0.06
    ಶ
    -0.06
    CVE
    -0.06
    POSITIVE LOGITS
     keine
    0.07
     sẽ
    0.07
    ée
    0.07
    的结果
    0.07
    .admin
    0.07
     TV
    0.07
    _ord
    0.07
    ę
    0.07
    ą
    0.07
     BOOLEAN
    0.07
    Act Density 0.011%

    No Known Activations