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

    Neuronpedia

    INDEX
    Explanations

    Detecting initials/abbreviations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _pt
    -0.07
    Possible
    -0.07
    Sexy
    -0.07
     opt
    -0.07
    incl
    -0.06
    _REPO
    -0.06
    暖
    -0.06
     Speech
    -0.06
     Kont
    -0.06
    ó
    -0.06
    POSITIVE LOGITS
    DRAM
    0.07
    posts
    0.06
    जन
    0.06
    PRESS
    0.06
    bler
    0.06
    љ
    0.06
     Sanayi
    0.06
     druhou
    0.06
     beers
    0.06
    โจ
    0.06
    Act Density 0.063%

    No Known Activations