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

    Neuronpedia

    INDEX
    Explanations

    check the box

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Syndrome
    0.43
     トップス
    0.43
     Grunge
    0.42
    بوون
    0.42
     ahuv
    0.41
    <unused86>
    0.41
     syndrome
    0.41
     ايا
    0.41
     syndromes
    0.40
    াজনক
    0.39
    POSITIVE LOGITS
    Reward
    0.45
    rewards
    0.44
     reward
    0.43
    reward
    0.43
     recompens
    0.43
     refund
    0.42
    footer
    0.40
     incentive
    0.38
    ft
    0.38
    enabled
    0.38
    Act Density 0.002%

    No Known Activations