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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    此种
    -0.08
     examine
    -0.07
    ュー
    -0.07
    .sex
    -0.07
     promoted
    -0.07
    剖析
    -0.07
    ורי
    -0.07
     Became
    -0.07
    Withdraw
    -0.07
    ecause
    -0.06
    POSITIVE LOGITS
     Lions
    0.07
    _gpu
    0.06
    wild
    0.06
    cas
    0.06
    +.
    0.06
     başlat
    0.06
    _least
    0.06
    !
↵
    0.06
    十个
    0.06
    缺席
    0.06
    Act Density 0.012%

    No Known Activations