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

    Neuronpedia

    INDEX
    Explanations

    angles and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DD
    -0.07
    923
    -0.07
     covariance
    -0.07
    기로
    -0.07
    .Decode
    -0.06
    ु
    -0.06
     Recursive
    -0.06
     Comm
    -0.06
    atories
    -0.06
     retarded
    -0.06
    POSITIVE LOGITS
     臺
    0.06
     Gecko
    0.06
     وإ
    0.06
     [...
    0.06
     dünyada
    0.06
    mc
    0.06
     minimise
    0.06
    (piece
    0.06
     {!!
    0.06
     Elsa
    0.06
    Act Density 0.053%

    No Known Activations