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

    Neuronpedia

    INDEX
    Explanations

    code, database interactions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MIME
    -0.07
    ón
    -0.07
    Most
    -0.07
    .json
    -0.06
     manus
    -0.06
    [G
    -0.06
    力
    -0.06
     RAF
    -0.06
    _COLOR
    -0.06
     pkg
    -0.06
    POSITIVE LOGITS
    言论
    0.07
     flats
    0.07
    ason
    0.07
    强硬
    0.07
     ansch
    0.07
    zn
    0.07
    时不时
    0.07
    сл
    0.06
    \API
    0.06
    чная
    0.06
    Act Density 0.001%

    No Known Activations