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

    Neuronpedia

    INDEX
    Explanations

    Formatting characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     önc
    -0.07
     सकत
    -0.07
     Ne
    -0.07
    bad
    -0.07
     On
    -0.07
    Launching
    -0.07
     donor
    -0.07
     keynote
    -0.07
    inar
    -0.06
    New
    -0.06
    POSITIVE LOGITS
    emm
    0.07
     suger
    0.07
    ella
    0.06
    م
    0.06
    getC
    0.06
     accommodations
    0.06
     감
    0.06
    ivist
    0.06
    linkplain
    0.06
     гум
    0.06
    Act Density 0.016%

    No Known Activations