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

    Neuronpedia

    INDEX
    Explanations

    code, file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Im
    -0.07
    πί
    -0.07
     Layer
    -0.06
     King
    -0.06
    وغ
    -0.06
    .pose
    -0.06
    ogl
    -0.06
     Kaz
    -0.06
     Carlos
    -0.06
     manga
    -0.06
    POSITIVE LOGITS
    *)_
    0.07
    ,$_
    0.06
     \(
    0.06
    privacy
    0.06
    чивается
    0.06
     STACK
    0.06
     законодатель
    0.06
     [$
    0.06
    .sup
    0.06
    {}↵
    0.06
    Act Density 0.000%

    No Known Activations