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

    Neuronpedia

    INDEX
    Explanations

    am

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oran
    -0.08
    剩下
    -0.07
     jóvenes
    -0.07
     Guinness
    -0.07
    OrUpdate
    -0.07
    osen
    -0.07
    Translation
    -0.06
     senior
    -0.06
    서
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    苡
    0.07
     carbs
    0.07
    五月
    0.07
    浓郁
    0.07
    .removeClass
    0.07
    (cuda
    0.07
    -txt
    0.07
    	ts
    0.07
    /ac
    0.07
    ڬ
    0.07
    Act Density 0.038%

    No Known Activations