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

    Neuronpedia

    INDEX
    Explanations

    rather

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cleaned
    -0.57
    Adults
    -0.53
     identified
    -0.52
     Adults
    -0.50
    borgs
    -0.49
     Packed
    -0.48
     moistened
    -0.48
     Masked
    -0.48
     labeled
    -0.47
     infected
    -0.47
    POSITIVE LOGITS
    webElementXpaths
    0.61
     competitiveness
    0.58
    ArgsConstructor
    0.58
     Philosophical
    0.57
     scholarship
    0.56
    URLException
    0.56
    produzione
    0.55
     insecurity
    0.54
     forgiveness
    0.54
     Auflage
    0.53
    Act Density 0.010%

    No Known Activations