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

    Neuronpedia

    INDEX
    Explanations

    neutral language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ducks
    -0.07
    	values
    -0.06
    digits
    -0.06
     we
    -0.06
     annually
    -0.06
    -inverse
    -0.06
     climbed
    -0.06
     imports
    -0.06
    .baomidou
    -0.06
    749
    -0.06
    POSITIVE LOGITS
    Houston
    0.07
    =edge
    0.06
    غن
    0.06
    ريس
    0.06
     chocolate
    0.06
     Period
    0.06
    <State
    0.06
    .configureTestingModule
    0.06
    -medium
    0.06
     distributor
    0.06
    Act Density 0.252%

    No Known Activations