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

    Neuronpedia

    INDEX
    Explanations

    bypasses and outlets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     leaders
    -0.07
     Tuple
    -0.06
    vision
    -0.06
    PTY
    -0.06
    _cash
    -0.06
     목
    -0.06
     CITY
    -0.06
     charter
    -0.06
    ливості
    -0.06
     cabins
    -0.06
    POSITIVE LOGITS
     ки
    0.06
     indust
    0.06
    ちら
    0.06
     참고
    0.06
    _fb
    0.06
     alignments
    0.06
    翻
    0.06
    Visit
    0.06
     repost
    0.06
    olución
    0.06
    Act Density 0.025%

    No Known Activations