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

    Neuronpedia

    INDEX
    Explanations

    say "the ending -ates/-at/-ory/-og"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     terme
    -0.06
    abilité
    -0.06
    <-
    -0.06
    	range
    -0.06
    .node
    -0.06
    coordinate
    -0.06
    /features
    -0.06
    мента
    -0.06
    DetailView
    -0.05
    <u
    -0.05
    POSITIVE LOGITS
     Мед
    0.07
     Occupation
    0.07
     Pablo
    0.07
     Swan
    0.07
     hab
    0.06
     Sequelize
    0.06
    adors
    0.06
     MPU
    0.06
     Hicks
    0.06
     Pazar
    0.06
    Act Density 0.003%

    No Known Activations