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

    Neuronpedia

    INDEX
    Explanations

    roll and subsequent actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    urnya
    0.49
    ua
    0.48
    metik
    0.48
    蒻
    0.48
    ноу
    0.46
    organisms
    0.45
    larından
    0.45
    UTRAL
    0.44
    arial
    0.44
    matmul
    0.44
    POSITIVE LOGITS
     rolling
    1.52
     roll
    1.45
    Roll
    1.41
     rolled
    1.40
     Rolling
    1.40
     Roll
    1.35
    Rolling
    1.32
    ROLL
    1.24
     ROLL
    1.21
     rollout
    1.18
    Act Density 0.020%

    No Known Activations