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

    Neuronpedia

    INDEX
    Explanations

    US

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Foundation
    -0.07
     excited
    -0.07
     adamant
    -0.07
     Schools
    -0.07
     Docker
    -0.07
    smooth
    -0.06
    :s
    -0.06
     corporations
    -0.06
     reflective
    -0.06
     เช
    -0.06
    POSITIVE LOGITS
     ."
    0.07
     retVal
    0.07
    }')
    0.07
    =}
    0.07
     EF
    0.07
     ??
    0.07
     viewed
    0.06
    镣
    0.06
     Sevent
    0.06
     Julie
    0.06
    Act Density 0.013%

    No Known Activations