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
     perder
    -0.07
     sizin
    -0.07
     Armor
    -0.06
    _GATE
    -0.06
     racer
    -0.06
     folly
    -0.06
    BD
    -0.06
     BRAND
    -0.06
    ==(
    -0.06
     pasture
    -0.06
    POSITIVE LOGITS
     comboBox
    0.07
    ̣
    0.06
     визначення
    0.06
    .curve
    0.06
     già
    0.06
    ographically
    0.06
    .unwrap
    0.06
    lanmıştır
    0.06
    chan
    0.06
    ARR
    0.06
    Act Density 0.000%

    No Known Activations