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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    userinfo
    -0.07
    ource
    -0.07
     tấn
    -0.07
    _run
    -0.07
     landsc
    -0.07
     cruise
    -0.06
     Hait
    -0.06
    (interval
    -0.06
    スー�
    -0.06
    整合
    -0.06
    POSITIVE LOGITS
    (Entity
    0.07
    死了
    0.07
     clad
    0.07
     essentials
    0.06
     Semaphore
    0.06
     ü
    0.06
     Targets
    0.06
     unmarried
    0.06
     tbl
    0.06
    UNUSED
    0.06
    Act Density 1.385%

    No Known Activations