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

    Neuronpedia

    INDEX
    Explanations

    terminal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🔇
    -0.07
    _READY
    -0.07
    _iters
    -0.07
     Equals
    -0.07
    oldem
    -0.07
    /pro
    -0.07
    穟
    -0.07
    過來
    -0.07
     ז
    -0.06
    浕
    -0.06
    POSITIVE LOGITS
    atics
    0.08
    编剧
    0.07
     Thinking
    0.07
     Knowing
    0.07
     at
    0.07
    了解到
    0.07
     measured
    0.07
     college
    0.06
    ref
    0.06
     retailer
    0.06
    Act Density 0.724%

    No Known Activations