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

    Neuronpedia

    INDEX
    Explanations

    research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     acquired
    -0.07
    quest
    -0.07
    pra
    -0.07
     follando
    -0.07
    mongoose
    -0.07
     nbr
    -0.06
    GW
    -0.06
    foon
    -0.06
    镮
    -0.06
     comics
    -0.06
    POSITIVE LOGITS
    Ӕ
    0.07
    ڔ
    0.07
    Ro
    0.07
    둑
    0.07
    ượt
    0.06
    לש
    0.06
    澳
    0.06
     Moż
    0.06
    ږ
    0.06
     họ
    0.06
    Act Density 0.312%

    No Known Activations