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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    串
    -0.07
    433
    -0.07
    rink
    -0.07
     State
    -0.06
    -e
    -0.06
     reverse
    -0.06
     grams
    -0.06
    State
    -0.06
     white
    -0.06
     assignment
    -0.06
    POSITIVE LOGITS
    ++++++++++++++++
    0.06
    ану
    0.06
    _loading
    0.06
    �
    0.06
    ##↵
    0.06
    <meta
    0.06
    辰
    0.06
    ocrin
    0.06
     ​​​
    0.06
    Calendar
    0.06
    Act Density 0.037%

    No Known Activations