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

    Neuronpedia

    INDEX
    Explanations

    despite

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     &___
    -0.80
     transfieras
    -0.79
     Monfieur
    -0.76
     Neander
    -0.75
     Shakspeare
    -0.72
     Saxons
    -0.71
    chyma
    -0.71
     فريبيس
    -0.70
    ReusableCell
    -0.70
    BibitemShut
    -0.69
    POSITIVE LOGITS
     throttle
    0.44
    marshaller
    0.44
     burner
    0.44
     thermocouple
    0.43
     power
    0.43
    ↵
    0.42
     catalyst
    0.40
     pump
    0.40
     DC
    0.40
     vent
    0.39
    Act Density 0.026%

    No Known Activations