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

    Neuronpedia

    INDEX
    Explanations

    cannot provide you with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     your
    0.73
    isons
    0.67
     gewüns
    0.65
     iyong
    0.62
    血压
    0.62
     suas
    0.62
    换
    0.61
     Your
    0.60
     serez
    0.60
     тво
    0.59
    POSITIVE LOGITS
     latte
    0.65
     lined
    0.63
     boarded
    0.63
     Arrays
    0.62
     Structured
    0.62
     programmed
    0.62
     karşılaş
    0.61
    structured
    0.61
     scheduled
    0.60
     Burial
    0.60
    Act Density 0.150%

    No Known Activations