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

    Neuronpedia

    INDEX
    Explanations

    expression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	sem
    -0.07
    tim
    -0.07
    !“
    -0.06
     bluff
    -0.06
     sû
    -0.06
     awhile
    -0.06
     hoje
    -0.06
    �택
    -0.06
    .beta
    -0.06
     dönem
    -0.06
    POSITIVE LOGITS
    _query
    0.07
     popup
    0.07
     Facts
    0.07
     ประก
    0.06
    цький
    0.06
    ющий
    0.06
     Fail
    0.06
     attempt
    0.06
     ofrece
    0.06
    Viewer
    0.06
    Act Density 0.000%

    No Known Activations