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

    Neuronpedia

    INDEX
    Explanations

    method

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    化身
    -0.08
    变身
    -0.07
    大街
    -0.07
    高速增长
    -0.06
     Affero
    -0.06
    罹
    -0.06
     tö
    -0.06
    靓丽
    -0.06
    肌肤
    -0.06
    ἵ
    -0.06
    POSITIVE LOGITS
    ,private
    0.07
    (attribute
    0.07
    [mid
    0.07
     american
    0.07
    vanized
    0.07
     __________________________________
    0.06
    Sphere
    0.06
    düğü
    0.06
    nett
    0.06
    경제
    0.06
    Act Density 0.010%

    No Known Activations