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

    Neuronpedia

    INDEX
    Explanations

    war

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     war
    -1.20
    beyond
    -0.93
     beyond
    -0.90
     Beyond
    -0.84
    Beyond
    -0.76
     War
    -0.69
     wars
    -0.65
     guerras
    -0.64
     guerra
    -0.64
     BEYOND
    -0.61
    POSITIVE LOGITS
    انيف
    0.69
     <>",
    0.68
    SharedDtor
    0.67
    AsUp
    0.63
    InstanceState
    0.61
    #
    0.61
     AssemblyCulture
    0.60
     myſelf
    0.59
    IsContent
    0.59
     Eſ
    0.59
    Act Density 0.072%

    No Known Activations