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

    Neuronpedia

    INDEX
    Explanations

    just

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Comprehensive
    -0.07
    _back
    -0.07
    -minute
    -0.06
    ,...↵
    -0.06
     ؟
    -0.06
     Alternative
    -0.06
     wreak
    -0.06
     Shelley
    -0.06
     olmam
    -0.06
    CHAN
    -0.06
    POSITIVE LOGITS
    овані
    0.07
    cre
    0.06
     Git
    0.06
    .tem
    0.06
     Unique
    0.06
    <Tag
    0.06
    alex
    0.06
     lbs
    0.06
    370
    0.06
     пері
    0.06
    Act Density 0.018%

    No Known Activations