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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     viewer
    -0.07
     zbo
    -0.07
     Basement
    -0.06
     islands
    -0.06
    aturdays
    -0.06
     с
    -0.06
    _cont
    -0.06
     ironically
    -0.06
     Courses
    -0.06
     поэтому
    -0.06
    POSITIVE LOGITS
     Gast
    0.07
    eking
    0.07
    ijo
    0.07
     AsyncCallback
    0.07
     '.$
    0.07
    완
    0.07
    edik
    0.06
     tom
    0.06
    .*(
    0.06
     accelerator
    0.06
    Act Density 0.027%

    No Known Activations