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

    Neuronpedia

    INDEX
    Explanations

    begin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     retiring
    -0.07
     '?'
    -0.07
     fase
    -0.07
    椀
    -0.07
    安心
    -0.07
     Skate
    -0.07
    .Ent
    -0.07
    Dates
    -0.07
     Wanted
    -0.06
     Affordable
    -0.06
    POSITIVE LOGITS
     Укра
    0.08
    aled
    0.08
    而后
    0.07
    ↵↵↵
    0.07
     لبنان
    0.07
    🐨
    0.07
     אומר
    0.06
     Lem
    0.06
    .ForeignKey
    0.06
    friends
    0.06
    Act Density 0.001%

    No Known Activations