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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TagHelper
    -0.77
    تقاوى
    -0.66
     transfieras
    -0.59
    InvalidProtocol
    -0.55
    شهاد
    -0.55
     betweenstory
    -0.54
    PMailer
    -0.54
    Rüyada
    -0.54
    ValueStyle
    -0.54
    MLLoader
    -0.54
    POSITIVE LOGITS
     consider
    0.85
     Consider
    0.75
    consider
    0.69
     CONSIDER
    0.68
    Consider
    0.66
     review
    0.64
     discuss
    0.63
     deal
    0.62
     consideran
    0.60
    review
    0.59
    Act Density 0.002%

    No Known Activations