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

    Neuronpedia

    INDEX
    Explanations

    File paths and URLs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rinse
    -0.08
     confession
    -0.07
    涅
    -0.07
    anchise
    -0.07
     Treatment
    -0.06
    &A
    -0.06
    呵
    -0.06
    lope
    -0.06
     limp
    -0.06
    芙
    -0.06
    POSITIVE LOGITS
    月中旬
    0.08
    }_${
    0.08
     окол
    0.07
     disks
    0.07
     $↵↵
    0.07
    .addColumn
    0.07
    (folder
    0.07
    ('^
    0.07
     Woche
    0.07
    物理
    0.07
    Act Density 0.003%

    No Known Activations