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

    Neuronpedia

    INDEX
    Explanations

    Em dash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nos
    -0.07
    Dev
    -0.07
     Rin
    -0.07
    べて
    -0.06
    addir
    -0.06
    obl
    -0.06
     �
    -0.06
     Piece
    -0.06
     parseInt
    -0.06
     трен
    -0.06
    POSITIVE LOGITS
    /{{$
    0.07
    UIT
    0.07
    HB
    0.07
    Comparable
    0.06
    orgh
    0.06
     Gab
    0.06
     comparer
    0.06
    uite
    0.06
    =".$
    0.06
     firearms
    0.06
    Act Density 0.005%

    No Known Activations