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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PLUGIN
    -0.07
     orden
    -0.07
     butto
    -0.07
    .extension
    -0.07
     суб
    -0.07
    .Failure
    -0.06
     Helen
    -0.06
    _gshared
    -0.06
     math
    -0.06
    .BorderSize
    -0.06
    POSITIVE LOGITS
    种
    0.07
    菜
    0.06
    联
    0.06
     빌
    0.06
    ?(
    0.06
    (post
    0.06
    965
    0.06
     mı
    0.06
    рек
    0.06
    ’te
    0.06
    Act Density 0.008%

    No Known Activations