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

    Neuronpedia

    INDEX
    Explanations

    function itself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    em
    0.56
    唕
    0.49
    ans
    0.49
     inconsc
    0.48
    čno
    0.47
     contrôler
    0.46
    ço
    0.45
    䜌
    0.45
    nb
    0.44
     সৌ
    0.44
    POSITIVE LOGITS
     मामूली
    0.43
    मूलन
    0.42
     Plenum
    0.42
     લ
    0.42
     stands
    0.42
     enclosures
    0.42
     Stands
    0.42
     Commodity
    0.41
     Seat
    0.41
    لك
    0.41
    Act Density 0.000%

    No Known Activations