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

    Neuronpedia

    INDEX
    Explanations

    diverse topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    521
    -0.07
    파일
    -0.06
     hr
    -0.06
     questi
    -0.06
    69
    -0.06
     percentage
    -0.06
    (events
    -0.06
     drinks
    -0.06
    画
    -0.06
    .heading
    -0.06
    POSITIVE LOGITS
    	die
    0.07
     unleash
    0.06
    .activities
    0.06
    ewitness
    0.06
     توانید
    0.06
    ottage
    0.06
    $obj
    0.06
    ()<<
    0.06
    �建
    0.06
    }`;↵↵
    0.06
    Act Density 0.087%

    No Known Activations