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

    Neuronpedia

    INDEX
    Explanations

    legal agreements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    噙
    -0.07
    _beam
    -0.07
    ân
    -0.07
    _IE
    -0.06
    (Button
    -0.06
    /temp
    -0.06
    	echo
    -0.06
     Po
    -0.06
    創新
    -0.06
     vox
    -0.06
    POSITIVE LOGITS
    週
    0.09
    昊
    0.08
     Adolescent
    0.07
    🇸
    0.07
     Fatal
    0.07
     Lars
    0.07
    _la
    0.07
    特斯
    0.07
    мещен
    0.07
    lógica
    0.07
    Act Density 0.013%

    No Known Activations