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

    Neuronpedia

    INDEX
    Explanations

    projects and tasks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Robert
    -0.06
     bins
    -0.06
    irus
    -0.06
    rooms
    -0.05
     Com
    -0.05
     enclosure
    -0.05
    505
    -0.05
    900
    -0.05
     simplement
    -0.05
    iatric
    -0.05
    POSITIVE LOGITS
     ↵ ↵
    0.07
    ujet
    0.07
     NUnit
    0.07
     boundary
    0.07
     Malaysian
    0.07
     Emotional
    0.07
    reo
    0.07
     edilm
    0.07
    __.
    0.06
    .parseLong
    0.06
    Act Density 0.002%

    No Known Activations