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

    Neuronpedia

    INDEX
    Explanations

    hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    %",↵
    -0.08
     cornerstone
    -0.07
     enfer
    -0.07
     tgt
    -0.07
    🎿
    -0.07
    	addr
    -0.07
     ofs
    -0.07
     fringe
    -0.07
     ayr
    -0.07
     molec
    -0.07
    POSITIVE LOGITS
    اته
    0.08
    上映
    0.08
    めた
    0.08
    _SL
    0.08
     conduct
    0.07
    SH
    0.07
    神
    0.07
     handic
    0.07
    (IM
    0.07
    _STATS
    0.07
    Act Density 0.063%

    No Known Activations