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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    联盟
    -0.06
     discour
    -0.06
    dling
    -0.06
    完
    -0.06
    -corner
    -0.06
     或
    -0.06
    曜日
    -0.06
    REDENTIAL
    -0.06
    {})
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     boots
    0.07
     Gerard
    0.07
     Ville
    0.07
     dun
    0.06
    equip
    0.06
     buggy
    0.06
     Ernest
    0.06
     Enrique
    0.06
     cane
    0.06
     gramm
    0.06
    Act Density 0.000%

    No Known Activations