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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
    aiser
    -0.08
    _B
    -0.07
     avait
    -0.07
    法国
    -0.07
    もし
    -0.07
     vaccinated
    -0.07
     restless
    -0.06
    .This
    -0.06
     ib
    -0.06
    一
    -0.06
    POSITIVE LOGITS
     alleles
    0.06
     standings
    0.06
    .addData
    0.06
     Neg
    0.06
     вели
    0.06
     Tracy
    0.06
     Skeleton
    0.06
     pageInfo
    0.06
     Lodge
    0.06
     subtitle
    0.06
    Act Density 0.463%

    No Known Activations