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

    Neuronpedia

    INDEX
    Explanations

    linking verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     upbeat
    -0.08
     نرم
    -0.07
     observer
    -0.07
     미국
    -0.07
     Garcia
    -0.06
    	filter
    -0.06
    Hum
    -0.06
    ateria
    -0.06
    593
    -0.06
    David
    -0.06
    POSITIVE LOGITS
     DEL
    0.07
    /payment
    0.06
    -about
    0.06
     =",
    0.06
     дем
    0.06
    лючается
    0.06
    .Claims
    0.06
     доз
    0.06
     Cous
    0.06
    <Guid
    0.06
    Act Density 0.042%

    No Known Activations