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

    Neuronpedia

    INDEX
    Explanations

    how we understand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     കൊണ്ട്
    0.52
     (
    0.48
    al
    0.47
    的
    0.44
     communications
    0.43
    ,
    0.43
     и
    0.41
    ссе
    0.41
     •
    0.41
     coaching
    0.40
    POSITIVE LOGITS
     pretzels
    0.48
    អារ
    0.46
    ત્ર
    0.45
     atribut
    0.44
     spesial
    0.44
    တယ်။
    0.44
     obvi
    0.44
     diferencial
    0.43
     esperienza
    0.43
     Pickle
    0.42
    Act Density 0.004%

    No Known Activations