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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ntag
    -0.07
    ounty
    -0.07
    ución
    -0.07
    FORMANCE
    -0.06
    ismic
    -0.06
    RefCount
    -0.06
    oltage
    -0.06
    acock
    -0.06
     Marian
    -0.06
    arded
    -0.06
    POSITIVE LOGITS
     alter
    0.06
    Dest
    0.06
     unreliable
    0.06
     نمودار
    0.06
    (labels
    0.06
    .В
    0.06
     trứng
    0.05
    .vel
    0.05
    ,st
    0.05
    通過
    0.05
    Act Density 0.007%

    No Known Activations