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

    Neuronpedia

    INDEX
    Explanations

    now

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aktiv
    -0.07
    enary
    -0.06
    坛
    -0.06
    nesty
    -0.06
    Sub
    -0.06
    andid
    -0.06
     منطقه
    -0.06
    ikt
    -0.06
    OVE
    -0.06
    ωμα
    -0.06
    POSITIVE LOGITS
    oulouse
    0.08
     bleeding
    0.07
     individually
    0.07
     btw
    0.07
     술
    0.07
     accordingly
    0.07
     достаточно
    0.07
    icut
    0.06
    idUser
    0.06
     پیوند
    0.06
    Act Density 0.000%

    No Known Activations