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

    Neuronpedia

    INDEX
    Explanations

    C++ code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     regain
    -0.07
     Both
    -0.07
    Peak
    -0.07
    項目
    -0.06
     kterého
    -0.06
    (changes
    -0.06
    laps
    -0.06
     który
    -0.06
     setzen
    -0.06
    renom
    -0.06
    POSITIVE LOGITS
    ौकर
    0.07
     TILE
    0.07
    @\
    0.07
    .HtmlControls
    0.06
     demonstrated
    0.06
    .sc
    0.06
    GetProcAddress
    0.06
    <()>
    0.06
     spare
    0.06
     applicationContext
    0.06
    Act Density 0.003%

    No Known Activations