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

    Neuronpedia

    INDEX
    Explanations

    Dragon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _measure
    -0.10
     Measure
    -0.08
     Mise
    -0.08
     Kib
    -0.08
     meubles
    -0.08
     Measurement
    -0.07
    Measure
    -0.07
    -me
    -0.07
    Implemented
    -0.07
     시행
    -0.07
    POSITIVE LOGITS
     dragons
    0.11
     dragon
    0.10
     liar
    0.09
     alati
    0.09
     uç
    0.08
     enormous
    0.08
    flight
    0.08
     विशाल
    0.08
     flight
    0.08
     inflatable
    0.08
    Act Density 0.009%

    No Known Activations