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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     connections
    -0.06
     consequential
    -0.06
    .calendar
    -0.06
    black
    -0.06
     UART
    -0.06
     prosperous
    -0.06
     ticaret
    -0.06
     grave
    -0.06
     информ
    -0.06
    _contrib
    -0.06
    POSITIVE LOGITS
     durumda
    0.07
     dp
    0.07
     případ
    0.07
     eller
    0.07
     Lilly
    0.07
     >/
    0.06
    *_
    0.06
    .|
    0.06
     กล
    0.06
     سک
    0.06
    Act Density 0.119%

    No Known Activations