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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    give
    -0.06
     Hector
    -0.06
     landed
    -0.06
     ATF
    -0.06
     Everybody
    -0.06
    泊
    -0.06
    责任
    -0.06
    甘
    -0.06
     descend
    -0.06
    Subset
    -0.06
    POSITIVE LOGITS
    ΙΚ
    0.06
    apanese
    0.06
    εκ
    0.06
    IE
    0.06
    endent
    0.06
     prototypes
    0.06
     humor
    0.06
     Người
    0.06
    níka
    0.06
    (arguments
    0.06
    Act Density 0.011%

    No Known Activations