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

    Neuronpedia

    INDEX
    Explanations

    x

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     swapped
    -0.07
     meth
    -0.07
     found
    -0.07
    笑道
    -0.07
     mundane
    -0.06
    率达到
    -0.06
    orted
    -0.06
     length
    -0.06
    lish
    -0.06
    古老
    -0.06
    POSITIVE LOGITS
    十四
    0.07
    乳业
    0.07
    started
    0.07
     Hurricane
    0.07
     двигат
    0.06
    积分
    0.06
     Cypress
    0.06
    .getDocument
    0.06
    追随
    0.06
     Dysfunction
    0.06
    Act Density 0.005%

    No Known Activations