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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Marshal
    -0.07
     Mar
    -0.07
     Separ
    -0.07
     INCIDENTAL
    -0.07
     ale
    -0.06
    ECH
    -0.06
     accessing
    -0.06
    _CLIENT
    -0.06
     Tub
    -0.06
    meta
    -0.06
    POSITIVE LOGITS
    =t
    0.07
     nulla
    0.07
    ]').
    0.07
    =val
    0.07
    ;}↵
    0.06
    (sigma
    0.06
     partnership
    0.06
    ียวก
    0.06
    亡
    0.06
    (pi
    0.06
    Act Density 0.032%

    No Known Activations