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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    formatter
    -0.08
     submitting
    -0.08
    ai
    -0.07
     NET
    -0.07
     philanthrop
    -0.07
     كنت
    -0.07
    -0.07
    oloj
    -0.07
     mạnh
    -0.07
    NET
    -0.07
    POSITIVE LOGITS
     intervalo
    0.08
    夏
    0.08
    岸
    0.08
     btn
    0.08
     arcs
    0.08
     osi
    0.08
     bc
    0.08
     hikes
    0.08
     FVector
    0.08
     walkway
    0.08
    Act Density 0.010%
    No Known Activations