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

    Neuronpedia

    INDEX
    Explanations

    language learning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     increasing
    -0.07
     якого
    -0.07
    .Pattern
    -0.07
    .True
    -0.06
     roky
    -0.06
     massasje
    -0.06
     CentOS
    -0.06
    िए
    -0.06
     Mundo
    -0.06
    _tokens
    -0.06
    POSITIVE LOGITS
    TOKEN
    0.07
    則
    0.06
     nour
    0.06
     propag
    0.06
     appel
    0.06
     tuples
    0.06
    нитель
    0.06
     "{\"
    0.05
    /articles
    0.05
     triangles
    0.05
    Act Density 0.018%

    No Known Activations