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

    Neuronpedia

    INDEX
    Explanations

    excel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Take
    -0.07
    download
    -0.07
     grave
    -0.07
    (change
    -0.07
     Console
    -0.07
     investigation
    -0.07
    (environment
    -0.07
     take
    -0.06
    valuate
    -0.06
     blonde
    -0.06
    POSITIVE LOGITS
     Machinery
    0.07
     축구
    0.06
    ampler
    0.06
    /dc
    0.06
    础
    0.06
    족
    0.06
    ATAB
    0.06
     persever
    0.06
     ‏
    0.06
    ดาว
    0.05
    Act Density 0.042%

    No Known Activations