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

    Neuronpedia

    INDEX
    Explanations

    code or data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bohydr
    -0.07
    �
    -0.06
     highlight
    -0.06
     innings
    -0.06
    -low
    -0.06
     shouldn
    -0.06
     Wine
    -0.06
     вкус
    -0.06
     contributing
    -0.06
     Knight
    -0.06
    POSITIVE LOGITS
     Memor
    0.07
     Anc
    0.07
    提交
    0.07
    ("#
    0.06
    읍
    0.06
     Narc
    0.06
     orally
    0.06
     Fant
    0.06
     탈
    0.06
    ِم
    0.06
    Act Density 0.037%

    No Known Activations