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

    Neuronpedia

    INDEX
    Explanations

    orphic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ℠
    -0.07
    \Context
    -0.07
     Кол
    -0.07
     endeavour
    -0.06
     certains
    -0.06
     Tất
    -0.06
    婢
    -0.06
     villagers
    -0.06
    户外
    -0.06
     reven
    -0.06
    POSITIVE LOGITS
     waits
    0.07
     REALLY
    0.07
    ربح
    0.07
    _right
    0.07
    Ready
    0.07
    _STRING
    0.07
    STER
    0.07
     QUERY
    0.07
     Whatever
    0.07
    Graph
    0.07
    Act Density 0.006%

    No Known Activations