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

    Neuronpedia

    INDEX
    Explanations

    copyright and license agreements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     autres
    -0.07
     instruction
    -0.07
     Cl
    -0.07
     preferences
    -0.06
    ihn
    -0.06
     libraries
    -0.06
     outlines
    -0.06
    101
    -0.06
     Terrain
    -0.06
     Mara
    -0.06
    POSITIVE LOGITS
     disg
    0.07
     NR
    0.07
     breve
    0.06
    IAM
    0.06
    ,state
    0.06
     olsa
    0.06
     (;;
    0.06
     dou
    0.06
    ันทร
    0.06
     clandest
    0.06
    Act Density 0.009%

    No Known Activations