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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    血管
    -0.07
     расход
    -0.07
     arms
    -0.07
    Ill
    -0.06
     input
    -0.06
    给别人
    -0.06
     boy
    -0.06
    拿来
    -0.06
    툩
    -0.06
     boon
    -0.06
    POSITIVE LOGITS
    🌴
    0.07
     APC
    0.07
    ]."
    0.07
    ismet
    0.07
    ocal
    0.07
     DOC
    0.07
     successful
    0.06
    (moment
    0.06
     yaklaşık
    0.06
    笊
    0.06
    Act Density 0.015%

    No Known Activations