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

    Neuronpedia

    INDEX
    Explanations

    executing or ways

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    repetitions
    0.45
    repeat
    0.40
    प्लो
    0.40
    tj
    0.39
     velocities
    0.39
    centres
    0.38
    的目的
    0.38
     tyres
    0.38
     centres
    0.38
     tires
    0.38
    POSITIVE LOGITS
    Week
    0.49
     Week
    0.48
    kimi
    0.44
    Bucket
    0.43
     '/
    0.41
     unu
    0.41
     разли
    0.41
     уда
    0.40
     бух
    0.40
     +'
    0.40
    Act Density 0.252%

    No Known Activations