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

    Neuronpedia

    INDEX
    Explanations

    positive in contrast or ironically

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     끝
    0.38
     మైసూరు
    0.38
    nurse
    0.37
     givenChar
    0.37
     nurse
    0.35
     Mead
    0.35
     placé
    0.35
    两侧
    0.35
     Quick
    0.35
     phenotypic
    0.35
    POSITIVE LOGITS
    Positive
    0.78
     positive
    0.72
    positive
    0.66
     positiva
    0.65
     positivas
    0.64
     Positive
    0.63
     positifs
    0.62
     pozitiv
    0.61
    POSITIVE
    0.61
     positivos
    0.59
    Act Density 0.009%

    No Known Activations