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

    Neuronpedia

    INDEX
    Explanations

    federation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Dark
    -0.06
    524
    -0.06
     highlight
    -0.06
    -work
    -0.06
    	ex
    -0.06
     Joyce
    -0.06
    $obj
    -0.06
     ص
    -0.05
    .Console
    -0.05
     monkeys
    -0.05
    POSITIVE LOGITS
     Federation
    0.11
     federation
    0.10
     feder
    0.08
     repetitions
    0.07
     Confeder
    0.07
    quotelev
    0.07
     görev
    0.07
     الاتحاد
    0.07
    ीवन
    0.07
    ederation
    0.07
    Act Density 0.005%

    No Known Activations