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

    Neuronpedia

    INDEX
    Explanations

    _version

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    具备
    -0.07
     spur
    -0.07
    _cov
    -0.07
    ɯ
    -0.07
     path
    -0.07
    中部
    -0.07
     tailor
    -0.06
     completes
    -0.06
     modest
    -0.06
     cache
    -0.06
    POSITIVE LOGITS
    .execution
    0.07
    احتجاج
    0.07
     Trotsky
    0.06
    רגש
    0.06
    информацион
    0.06
    烈
    0.06
    ERY
    0.06
     rebels
    0.06
    �
    0.06
     المح
    0.06
    Act Density 0.000%

    No Known Activations