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

    Neuronpedia

    INDEX
    Explanations

    CF, SE, RC, EU, SU, XY, TS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gpg
    0.61
    lcc
    0.60
    BBB
    0.58
    tpc
    0.57
    PPP
    0.57
    DDD
    0.57
    ppp
    0.56
    FFF
    0.55
    CCL
    0.55
    CQL
    0.55
    POSITIVE LOGITS
     SM
    0.57
     BC
    0.56
     CS
    0.54
     SD
    0.54
     CC
    0.54
     ВС
    0.53
     SC
    0.52
    Ｍ
    0.52
     SP
    0.51
     MB
    0.51
    Act Density 0.654%

    No Known Activations