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

    Neuronpedia

    INDEX
    Explanations

    stopwords

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alis
    -0.07
     gastric
    -0.07
    ampp
    -0.07
    .itemId
    -0.07
    blade
    -0.06
     translator
    -0.06
     skeptic
    -0.06
    udas
    -0.06
    rac
    -0.06
    node
    -0.06
    POSITIVE LOGITS
     dispos
    0.06
     mainly
    0.06
     Mayıs
    0.05
    paced
    0.05
     Protect
    0.05
    Stopping
    0.05
     nuestras
    0.05
     Months
    0.05
     {},
    0.05
    irate
    0.05
    Act Density 0.081%

    No Known Activations