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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to academic research and data presentation, including showing results

    oai_token-act-pair · gemini-2.0-flash

    show

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    abestanden
    -0.57
    NewUrlParser
    -0.57
    )}}{
    -0.56
    wole
    -0.55
     devriez
    -0.55
    avenir
    -0.53
    Bans
    -0.52
     effort
    -0.51
     архивлан
    -0.51
    lasser
    -0.50
    POSITIVE LOGITS
    apunov
    0.64
     defaultstate
    0.63
    MemoryWarning
    0.63
    μως
    0.60
    getWriter
    0.59
    NOPQRST
    0.59
    didSet
    0.59
    TacToe
    0.57
    enderror
    0.57
     Goodreads
    0.56
    Act Density 0.848%

    No Known Activations