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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FullYear
    -0.07
     Ш
    -0.07
     forme
    -0.07
    LABEL
    -0.06
    Zh
    -0.06
    Displayed
    -0.06
    YRO
    -0.06
     stoi
    -0.06
     Ik
    -0.06
     Ст
    -0.06
    POSITIVE LOGITS
     outfield
    0.07
     arası
    0.06
    hurst
    0.06
     japon
    0.06
     onOptionsItemSelected
    0.06
    net
    0.06
    ;↵
    0.06
     fresh
    0.06
     };↵
    0.06
    edeki
    0.06
    Act Density 0.008%

    No Known Activations