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

    Neuronpedia

    INDEX
    Explanations

    1: itesmary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    orems
    0.39
     komen
    0.38
    مارات
    0.38
     угодно
    0.38
    bery
    0.37
     programmes
    0.37
     spp
    0.37
     aufge
    0.36
     literat
    0.35
     svak
    0.35
    POSITIVE LOGITS
     Episode
    0.61
     November
    0.53
     Featuring
    0.51
     episode
    0.51
    Episode
    0.50
     July
    0.50
    聚焦
    0.49
     featuring
    0.48
     October
    0.48
     "~
    0.48
    Act Density 0.050%

    No Known Activations