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

    Neuronpedia

    INDEX
    Explanations

    No Confirmed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     magia
    0.57
     altra
    0.53
     ahí
    0.49
     önemlidir
    0.49
     ভারসাম্য
    0.47
    AL
    0.47
    അ
    0.47
    »).
    0.46
     diğer
    0.46
     أخرى
    0.46
    POSITIVE LOGITS
     commotion
    0.46
    ^{
    0.45
     vid
    0.44
     peered
    0.43
     sighed
    0.41
     stunned
    0.41
     cascade
    0.41
     skyrocketed
    0.40
    פ
    0.40
     enrolled
    0.39
    Act Density 0.053%

    No Known Activations