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

    Neuronpedia

    INDEX
    Explanations

    works and plurals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    简便
    -0.07
    (LogLevel
    -0.07
    替补
    -0.07
    getHeight
    -0.07
     Bear
    -0.07
    roups
    -0.07
     Resist
    -0.06
     Ready
    -0.06
    onaut
    -0.06
    chief
    -0.06
    POSITIVE LOGITS
     SQL
    0.07
    り
    0.07
    /do
    0.07
    holes
    0.07
     calculated
    0.07
    だったら
    0.07
    альных
    0.07
     illicit
    0.07
    igated
    0.07
    词条
    0.07
    Act Density 0.000%

    No Known Activations