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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    键
    -0.07
     Orn
    -0.07
     creepy
    -0.07
    _numbers
    -0.07
    집
    -0.07
    طلب
    -0.07
     кри
    -0.07
     Axes
    -0.07
    .Nodes
    -0.06
     νε
    -0.06
    POSITIVE LOGITS
     adec
    0.06
    /host
    0.06
    /welcome
    0.06
    leftJoin
    0.06
    known
    0.06
    광역시
    0.06
    ã
    0.06
     confidentiality
    0.06
    esini
    0.06
    ное
    0.06
    Act Density 0.049%

    No Known Activations