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

    Neuronpedia

    INDEX
    Explanations

    quantity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     {}).
    -0.28
    nez
    -0.26
    .proto
    -0.26
    ({})↵
    -0.26
    Wel
    -0.25
    wed
    -0.24
    weg
    -0.24
    çĶŁæ´»çļĦ
    -0.24
    <&
    -0.24
    lish
    -0.24
    POSITIVE LOGITS
    cmds
    0.25
    æŁIJç§įç¨ĭ度
    0.25
     harmless
    0.24
    ORMAT
    0.24
     casc
    0.24
    é¡·
    0.24
    indr
    0.23
    è¿Ļä¹Ł
    0.23
    ourke
    0.23
     trickle
    0.23
    Act Density 0.007%

    No Known Activations