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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    reme
    -0.06
     puck
    -0.06
    Plus
    -0.06
     선
    -0.06
    (Server
    -0.06
    ponsors
    -0.06
    тив
    -0.06
     revived
    -0.06
     předmět
    -0.06
     dispens
    -0.05
    POSITIVE LOGITS
    .addChild
    0.08
    ................................
    0.07
    Throughout
    0.07
    емати
    0.07
     popularity
    0.06
    .assertj
    0.06
    Tuy
    0.06
     partitions
    0.06
     náměstí
    0.06
    Clients
    0.06
    Act Density 0.004%

    No Known Activations