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

    Neuronpedia

    INDEX
    Explanations

    court cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    یان
    -0.07
     HID
    -0.07
    estring
    -0.07
    >#
    -0.06
    .ids
    -0.06
    )).↵
    -0.06
     freder
    -0.06
    leyen
    -0.06
    "While
    -0.06
     Müslüman
    -0.06
    POSITIVE LOGITS
     Emergency
    0.07
     الات
    0.07
    .uri
    0.06
    Editable
    0.06
    olls
    0.06
    머
    0.06
    LIC
    0.06
     đứ
    0.06
    ดน
    0.06
     상담
    0.06
    Act Density 0.004%

    No Known Activations