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

    Neuronpedia

    INDEX
    Explanations

    Plus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     curriculum
    -0.06
     sự
    -0.06
     Chick
    -0.06
     Yep
    -0.06
     McGill
    -0.06
    変
    -0.06
    خدام
    -0.06
    bullet
    -0.06
     đu
    -0.06
    .Function
    -0.06
    POSITIVE LOGITS
     looping
    0.07
    _avatar
    0.06
    _focus
    0.06
    /access
    0.06
    _AM
    0.06
     Antique
    0.06
    .stdin
    0.06
     núi
    0.06
     nonzero
    0.06
     nodes
    0.05
    Act Density 0.063%

    No Known Activations