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

    Neuronpedia

    INDEX
    Explanations

    split

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ypos
    -0.06
    回到
    -0.06
    [node
    -0.06
     eos
    -0.06
    不知道
    -0.06
     conect
    -0.06
    (pg
    -0.06
    .objects
    -0.06
    クト
    -0.06
    gether
    -0.06
    POSITIVE LOGITS
     proposition
    0.07
    excerpt
    0.07
    ↵			↵
    0.07
     propositions
    0.07
     euth
    0.07
    :test
    0.06
    (events
    0.06
    ("~/
    0.06
    밀
    0.06
     Revel
    0.06
    Act Density 0.002%

    No Known Activations