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

    Neuronpedia

    INDEX
    Explanations

    Service contracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    baseline
    -0.07
     flying
    -0.07
    _elem
    -0.06
    افية
    -0.06
    梅
    -0.06
     Card
    -0.06
     Poh
    -0.06
    능
    -0.06
    ("\(
    -0.06
    朋友
    -0.06
    POSITIVE LOGITS
    (docs
    0.07
     Kendall
    0.07
    Detection
    0.07
     Sniper
    0.06
    Advertisements
    0.06
    executable
    0.06
    tiles
    0.06
    -online
    0.06
     yahoo
    0.06
    .Are
    0.06
    Act Density 0.024%

    No Known Activations