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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	ctrl
    -0.08
     expertise
    -0.08
    fruit
    -0.07
    ources
    -0.07
    Screen
    -0.07
    	ArrayList
    -0.07
    trial
    -0.07
    finger
    -0.07
    	ptr
    -0.07
     Santo
    -0.07
    POSITIVE LOGITS
     由
    0.07
     رسم
    0.07
     Pose
    0.06
    ェ
    0.06
    جاد
    0.06
    스의
    0.06
    меть
    0.06
    ันเป
    0.06
    abe
    0.06
    зна
    0.06
    Act Density 0.033%

    No Known Activations