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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     planning
    -0.06
    북
    -0.06
    Special
    -0.06
     Moses
    -0.06
     był
    -0.06
    Como
    -0.06
     名
    -0.06
     Making
    -0.06
     bych
    -0.06
    /xml
    -0.06
    POSITIVE LOGITS
    .Generated
    0.07
     cad
    0.07
    =str
    0.07
     raspberry
    0.06
    CLUSION
    0.06
    bildung
    0.06
    خرى
    0.06
     Cad
    0.06
     reh
    0.06
     Clo
    0.06
    Act Density 0.068%

    No Known Activations