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

    Neuronpedia

    INDEX
    Explanations

    reportedly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Effectively
    -0.93
    presumably
    -0.90
     Presumably
    -0.87
     presumably
    -0.87
     Paglinawan
    -0.82
     reportedly
    -0.81
     supuestamente
    -0.80
     effectively
    -0.78
    effectively
    -0.76
     famously
    -0.75
    POSITIVE LOGITS
     speaking
    0.67
     growing
    0.52
     grew
    0.52
     grown
    0.50
     Speaking
    0.49
     infected
    0.48
     grow
    0.47
    تام
    0.46
     Malaria
    0.45
    umato
    0.45
    Act Density 0.093%

    No Known Activations