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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Form
    -0.07
    brand
    -0.07
    ὃ
    -0.07
    ubernetes
    -0.07
    终身
    -0.07
     shore
    -0.07
    一季度
    -0.07
    Franc
    -0.07
    即使
    -0.07
     submitting
    -0.07
    POSITIVE LOGITS
    (Expected
    0.08
    的喜爱
    0.07
    郁闷
    0.07
     Ay
    0.07
     wreckage
    0.07
    .INTER
    0.07
     yürüt
    0.07
     tatsäch
    0.07
    ご�
    0.07
     aftermath
    0.06
    Act Density 0.009%

    No Known Activations