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

    Neuronpedia

    INDEX
    Explanations

    programming languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sendMessage
    -0.07
    usta
    -0.06
    _hot
    -0.06
     школ
    -0.06
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    -0.06
    (te
    -0.06
     вже
    -0.06
    /span
    -0.06
     cảnh
    -0.06
    agenda
    -0.06
    POSITIVE LOGITS
     무료
    0.07
     Addresses
    0.07
     وغير
    0.07
    『
    0.06
    riendly
    0.06
    �
    0.06
    PR
    0.06
     повинен
    0.06
    ]:↵
    0.06
    WR
    0.06
    Act Density 0.027%

    No Known Activations