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

    Neuronpedia

    INDEX
    Explanations

    sharing, resource sharing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    铉
    0.40
     kicker
    0.39
     Márquez
    0.39
     shared
    0.38
     kicked
    0.38
     mutual
    0.37
     Healey
    0.36
     kick
    0.36
    shared
    0.35
    裔
    0.35
    POSITIVE LOGITS
     Cond
    1.29
    Cond
    1.25
     cond
    1.12
     COND
    1.09
     kond
    1.01
    cond
    0.99
     Kond
    0.90
     condens
    0.86
    COND
    0.84
     конденса
    0.83
    Act Density 0.001%

    No Known Activations