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
     рабо
    -0.07
     книж
    -0.07
     тра
    -0.06
    营业
    -0.06
    _partial
    -0.06
     Associ
    -0.06
     Všech
    -0.06
    .mark
    -0.06
     RB
    -0.06
    .dictionary
    -0.06
    POSITIVE LOGITS
    ево
    0.07
    ピ
    0.07
    ################
    0.06
     ****************
    0.06
    ISHED
    0.06
    ushi
    0.06
     #
    0.06
     حدود
    0.06
     transporting
    0.06
     engineered
    0.06
    Act Density 0.000%

    No Known Activations