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

    Neuronpedia

    INDEX
    Explanations

    question and code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ))))
    -0.07
    ˮ
    -0.07
    uters
    -0.07
    侵害
    -0.07
    ﭫ
    -0.07
     »,
    -0.07
    Vu
    -0.07
    ﾒ
    -0.06
    公用
    -0.06
    amate
    -0.06
    POSITIVE LOGITS
    Comm
    0.07
     bombs
    0.07
     CENT
    0.07
     איתו
    0.07
    major
    0.07
     corn
    0.07
    .Pay
    0.06
    Eff
    0.06
    [obj
    0.06
    	std
    0.06
    Act Density 0.009%

    No Known Activations