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

    Neuronpedia

    INDEX
    Explanations

    Failure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    phinx
    -0.08
    这就
    -0.07
     -,
    -0.07
     licensors
    -0.07
    		↵		↵		↵
    -0.07
    ×</
    -0.06
     Nutrition
    -0.06
    融合发展
    -0.06
    תוך
    -0.06
    综
    -0.06
    POSITIVE LOGITS
    燚
    0.08
    atore
    0.08
    ポ
    0.08
     Ramirez
    0.07
    院长
    0.07
    	GLuint
    0.07
     stressful
    0.07
    痊
    0.07
     Ster
    0.07
    born
    0.07
    Act Density 0.010%

    No Known Activations