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

    Neuronpedia

    INDEX
    Explanations

    message authentication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Brist
    0.49
     Robotics
    0.46
    ﯽ
    0.44
    ロボ
    0.44
    マップ
    0.42
    越
    0.40
     ఛ
    0.40
     كيف
    0.40
     Cp
    0.40
     ഉള്ള
    0.39
    POSITIVE LOGITS
     smells
    0.45
     yar
    0.41
     taxed
    0.39
    ysis
    0.38
     taxes
    0.37
     undergoing
    0.35
     frag
    0.35
    ün
    0.34
     đột
    0.34
     হামিদ
    0.34
    Act Density 0.001%

    No Known Activations