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

    Neuronpedia

    INDEX
    Explanations

    Cup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (writer
    -0.07
    ley
    -0.07
    LEY
    -0.07
    嘴
    -0.07
     umb
    -0.07
     além
    -0.07
     bothers
    -0.06
    侧
    -0.06
     Hartford
    -0.06
    .drag
    -0.06
    POSITIVE LOGITS
     ゝ
    0.07
    :mm
    0.07
    /csv
    0.07
    .Cursors
    0.06
     ADM
    0.06
    GV
    0.06
    aat
    0.06
     "$
    0.06
    .....
    0.06
     сов
    0.06
    Act Density 0.003%

    No Known Activations