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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    indsay
    -0.08
    っち
    -0.08
     Doyle
    -0.07
    criptive
    -0.07
    manuel
    -0.07
    KEN
    -0.07
    蓝天
    -0.06
    ことがあります
    -0.06
    רצ
    -0.06
    (prop
    -0.06
    POSITIVE LOGITS
     invalidated
    0.07
     idol
    0.07
    成長
    0.07
    Reflection
    0.07
     gridView
    0.06
    >())↵
    0.06
    orderId
    0.06
    >$
    0.06
    ']:↵
    0.06
     השבוע
    0.06
    Act Density 0.003%

    No Known Activations