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

    Neuronpedia

    INDEX
    Explanations

    code and symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     submitted
    -0.07
    贴
    -0.07
    �
    -0.06
     cones
    -0.06
    κη
    -0.06
     provinc
    -0.06
     تغییر
    -0.06
     年
    -0.06
     міської
    -0.06
    êm
    -0.06
    POSITIVE LOGITS
     pygame
    0.06
     Barker
    0.06
    ]
↵
    0.06
    "↵↵↵
    0.06
     JPanel
    0.06
     DOWN
    0.06
     movements
    0.06
     Hebrew
    0.06
    zm
    0.06
    Mage
    0.06
    Act Density 0.015%

    No Known Activations