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

    Neuronpedia

    INDEX
    Explanations

    Beginning of sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     представ
    -0.07
    发展
    -0.07
     attractive
    -0.07
    他の
    -0.06
     conoc
    -0.06
     ж
    -0.06
    agem
    -0.06
    (operation
    -0.06
     their
    -0.06
    诗
    -0.06
    POSITIVE LOGITS
    	min
    0.07
    };↵↵
    0.07
    `↵
    0.06
    	delete
    0.06
     �
    0.06
     أش
    0.06
     Collapse
    0.06
    ："+
    0.06
    Settings
    0.06
     "__
    0.06
    Act Density 0.246%

    No Known Activations