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

    Neuronpedia

    INDEX
    Explanations

    Code/Technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DI
    -0.07
    №№
    -0.06
    icipation
    -0.06
     smoothing
    -0.06
    Př
    -0.06
     NIL
    -0.06
     свобод
    -0.06
     Ain
    -0.06
     IMF
    -0.06
    NIL
    -0.06
    POSITIVE LOGITS
    イヤ
    0.07
     POINT
    0.06
    (uri
    0.06
    (csv
    0.06
     Point
    0.06
     prm
    0.06
     Escort
    0.06
    古屋
    0.06
     Fuck
    0.06
    eurs
    0.06
    Act Density 0.000%

    No Known Activations