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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kf
    -0.07
    tpl
    -0.07
    gle
    -0.07
    甲
    -0.06
    JK
    -0.06
     Imported
    -0.06
    핥
    -0.06
    𝐉
    -0.06
     Husband
    -0.06
    inspect
    -0.06
    POSITIVE LOGITS
    рут
    0.07
     истор
    0.07
     raises
    0.07
    yclopedia
    0.07
     chiều
    0.07
    七个
    0.07
     leftist
    0.06
     Cosmos
    0.06
    髅
    0.06
    Trader
    0.06
    Act Density 0.030%

    No Known Activations