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

    Neuronpedia

    INDEX
    Explanations

    book references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bài
    -0.06
    Dependencies
    -0.06
     покуп
    -0.06
     이상
    -0.06
     Fax
    -0.06
     kadar
    -0.06
    (post
    -0.06
    bindung
    -0.06
    ffset
    -0.06
     Tuple
    -0.06
    POSITIVE LOGITS
     impressed
    0.06
     dois
    0.06
     swept
    0.06
     demolished
    0.06
     spotted
    0.06
    ATRIX
    0.06
     admir
    0.06
     alerted
    0.06
    æk
    0.06
     journeys
    0.06
    Act Density 0.042%

    No Known Activations