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

    Neuronpedia

    INDEX
    Explanations

    marked

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     marked
    -1.59
    marked
    -1.55
     marks
    -1.52
     marking
    -1.37
    marks
    -1.29
     Marked
    -1.21
    Marks
    -1.15
     Marks
    -1.11
    Marked
    -1.10
    marking
    -1.07
    POSITIVE LOGITS
    Autoritní
    0.79
    ness
    0.66
    出版年
    0.63
     dreamstime
    0.62
    Sucesor
    0.60
    ization
    0.60
     geox
    0.60
    исленность
    0.59
     bounties
    0.59
     nonUne
    0.59
    Act Density 0.067%

    No Known Activations