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

    Neuronpedia

    INDEX
    Explanations

    fires

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prezzo
    -0.10
     précieux
    -0.09
     valore
    -0.09
     വില
    -0.09
     preço
    -0.09
     presyo
    -0.09
     priced
    -0.09
     prix
    -0.08
    prix
    -0.08
     poetry
    -0.08
    POSITIVE LOGITS
     техники
    0.08
     unattended
    0.08
     needles
    0.08
     الأص
    0.08
     introductions
    0.08
    wam
    0.07
     housekeeping
    0.07
     Sust
    0.07
     убед
    0.07
     అంట
    0.07
    Act Density 0.011%

    No Known Activations