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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yn
    -0.07
    없는
    -0.07
    __),
    -0.07
    Portland
    -0.06
    Wy
    -0.06
    ительные
    -0.06
    >();
↵
↵
    -0.06
     iki
    -0.06
    "))↵
    -0.06
     있다
    -0.06
    POSITIVE LOGITS
     rewriting
    0.07
    레
    0.06
     dubbed
    0.06
     벽
    0.06
    (ind
    0.06
     milestones
    0.06
     preprocessing
    0.06
     peptides
    0.06
    ponsor
    0.06
    挑
    0.06
    Act Density 0.006%

    No Known Activations