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

    Neuronpedia

    INDEX
    Explanations

    def

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ­های
    -0.06
     Fin
    -0.06
     giveaway
    -0.06
     grouped
    -0.06
    ráci
    -0.05
     pickups
    -0.05
    zem
    -0.05
     української
    -0.05
     inconvenience
    -0.05
    แนะ
    -0.05
    POSITIVE LOGITS
     del
    0.08
     Δ
    0.07
     ba
    0.07
     Nora
    0.06
     ikt
    0.06
     {
    0.06
     個
    0.06
    rire
    0.06
     posicion
    0.06
    ressed
    0.06
    Act Density 0.022%

    No Known Activations