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

    Neuronpedia

    INDEX
    Explanations

    Age

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ERGE
    -0.06
     Kazakhstan
    -0.06
    NX
    -0.06
     ARM
    -0.06
    gien
    -0.06
     EV
    -0.06
     vậy
    -0.05
    avier
    -0.05
     ligne
    -0.05
     Penny
    -0.05
    POSITIVE LOGITS
    369
    0.07
    372
    0.07
     Tactics
    0.07
     ()->
    0.07
     ödeme
    0.07
    phia
    0.07
     tuo
    0.07
     priorities
    0.06
    会
    0.06
    claim
    0.06
    Act Density 0.023%

    No Known Activations