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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ']);
    -0.07
    专业
    -0.07
     号
    -0.06
    _nbr
    -0.06
    114
    -0.06
    bih
    -0.06
    Increased
    -0.06
     الجم
    -0.06
    418
    -0.06
     걸
    -0.06
    POSITIVE LOGITS
     Clarence
    0.07
    	module
    0.07
     softened
    0.06
     validations
    0.06
    nostic
    0.06
     flask
    0.06
    	source
    0.06
    只能
    0.06
    ีน
    0.06
    -coded
    0.06
    Act Density 0.005%

    No Known Activations