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

    Neuronpedia

    INDEX
    Explanations

    annotation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    柄
    -0.07
    _cell
    -0.07
    istrict
    -0.07
     Parallel
    -0.07
    ู
    -0.07
     �
    -0.06
     zboží
    -0.06
    FE
    -0.06
    oin
    -0.06
    يكا
    -0.06
    POSITIVE LOGITS
    _operation
    0.07
     announce
    0.07
     rund
    0.07
    Dear
    0.06
     =~
    0.06
     protester
    0.06
     Observation
    0.06
    olleyError
    0.06
    >");↵
    0.06
    istinguished
    0.06
    Act Density 0.003%

    No Known Activations