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

    Neuronpedia

    INDEX
    Explanations

    nuclear weapons/war

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .**************
    -0.07
     QUAL
    -0.07
    ETH
    -0.07
     contentious
    -0.06
    KO
    -0.06
     سری
    -0.06
    еры
    -0.06
    eliness
    -0.06
     monitored
    -0.06
     الدولة
    -0.06
    POSITIVE LOGITS
     '')
    0.07
     allegations
    0.07
    "]."
    0.07
     Belgian
    0.06
     Cre
    0.06
    .ax
    0.06
     Communist
    0.06
    Month
    0.06
     '../
    0.06
     ji
    0.06
    Act Density 0.030%

    No Known Activations