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

    Neuronpedia

    INDEX
    Explanations

    computer code/data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    병
    -0.08
    𬶨
    -0.08
    cmpeq
    -0.07
    /create
    -0.07
    ="/
    -0.07
    在整个
    -0.07
    进入到
    -0.07
    התפתחות
    -0.07
    orderBy
    -0.06
    цеп
    -0.06
    POSITIVE LOGITS
     cob
    0.08
     Calder
    0.07
     Para
    0.07
    _ed
    0.07
    黄色
    0.07
     San
    0.07
     OST
    0.07
     Sil
    0.07
     Atlanta
    0.07
    _statement
    0.07
    Act Density 0.005%

    No Known Activations