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

    Neuronpedia

    INDEX
    Explanations

    grow to solve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CURSOR
    0.40
     нале
    0.37
     माम
    0.37
    БУ
    0.37
    设有
    0.37
    㐬
    0.36
    LLAR
    0.36
     ولو
    0.36
    知的
    0.35
    それぞれ
    0.35
    POSITIVE LOGITS
    cleaned
    0.43
     diagram
    0.41
    cd
    0.41
     cleaned
    0.38
     समीक्षा
    0.37
     eventdata
    0.37
     purified
    0.37
    opens
    0.36
     avvic
    0.36
     obu
    0.36
    Act Density 0.000%

    No Known Activations