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

    Neuronpedia

    INDEX
    Explanations

    computer code/data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Trials
    -0.07
    imations
    -0.06
     TAX
    -0.06
     qualification
    -0.06
    Unload
    -0.06
     Notice
    -0.06
     ordinal
    -0.06
     rollers
    -0.06
     khá
    -0.06
     scrolling
    -0.06
    POSITIVE LOGITS
    ー
    0.07
     вет
    0.07
    substr
    0.07
    _altern
    0.06
     Canadian
    0.06
    색
    0.06
    ])↵↵
    0.06
    険
    0.06
    út
    0.06
     istiyorum
    0.06
    Act Density 0.055%

    No Known Activations