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

    Neuronpedia

    INDEX
    Explanations

    cell membrane extensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MGM
    0.74
    Deer
    0.69
    ন্যা
    0.68
     кварта
    0.67
    ባቸው
    0.67
    Jer
    0.65
    Ski
    0.64
    Equals
    0.64
    жет
    0.64
    Луч
    0.64
    POSITIVE LOGITS
    大陆
    0.79
    铖
    0.77
     capturedPlayer
    0.74
     coeffs
    0.72
     ভাষণ
    0.71
    解释
    0.71
    ฀
    0.69
    经典的
    0.69
    0.68
     subgoal
    0.67
    Act Density 0.000%

    No Known Activations