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

    Neuronpedia

    INDEX
    Explanations

    say number 23

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '],↵↵
    -0.07
    oren
    -0.07
    Private
    -0.06
     kak
    -0.06
     cree
    -0.06
     thinks
    -0.06
    actor
    -0.06
    meter
    -0.06
    _rc
    -0.06
    cleanup
    -0.06
    POSITIVE LOGITS
    に対
    0.07
     المس
    0.06
    จากการ
    0.06
    に関
    0.06
     stringBy
    0.06
    ellation
    0.06
     quarterly
    0.06
     Yugoslavia
    0.06
     cauliflower
    0.06
     echoed
    0.05
    Act Density 0.034%

    No Known Activations