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

    Neuronpedia

    INDEX
    Explanations

    setting text content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getJSONObject
    1.83
    ون
    1.76
    ு
    1.74
     algebras
    1.67
    یز
    1.66
    යේ
    1.62
     وج
    1.61
    एक
    1.59
    ક
    1.59
     участ
    1.58
    POSITIVE LOGITS
    lere
    2.07
    lier
    1.91
    ž
    1.69
     Absolutely
    1.69
    ങ്കി
    1.63
    lichkeit
    1.62
    ם
    1.61
    Oy
    1.58
     scape
    1.58
     pied
    1.54
    Act Density 0.007%

    No Known Activations