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

    Neuronpedia

    INDEX
    Explanations

    wine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    budget
    -0.07
     bind
    -0.07
    ificates
    -0.06
    parated
    -0.06
     مق
    -0.06
     Vegetable
    -0.06
    Creature
    -0.06
    니다
    -0.06
    	↵		↵
    -0.06
    sth
    -0.06
    POSITIVE LOGITS
    _prefix
    0.07
    에서
    0.07
     Patel
    0.06
    figure
    0.06
    _Framework
    0.06
     инвести
    0.06
     lithium
    0.06
    勢
    0.06
    $max
    0.06
    445
    0.06
    Act Density 0.023%

    No Known Activations