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

    Neuronpedia

    INDEX
    Explanations

    support creators and clubs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    supporters
    0.43
     follower
    0.42
    supports
    0.42
     अन्याय
    0.42
     unterstützt
    0.41
     sostegno
    0.41
     followers
    0.41
    soc
    0.41
    followers
    0.41
     solicitors
    0.41
    POSITIVE LOGITS
     Buy
    0.43
     Carlson
    0.42
    ค
    0.41
    Buy
    0.41
     Rach
    0.40
    땐
    0.40
     Henrietta
    0.39
     Carl
    0.39
    Foods
    0.38
     Conrad
    0.38
    Act Density 0.002%

    No Known Activations