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

    Neuronpedia

    INDEX
    Explanations

    social media and github links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Com
    0.65
     COM
    0.61
    Com
    0.58
     coma
    0.57
     Comer
    0.55
     кома
    0.54
    コミ
    0.53
     Comet
    0.53
    COM
    0.51
    कॉम
    0.51
    POSITIVE LOGITS
    ~/
    0.40
    __/
    0.40
    ]/
    0.40
     '
    0.38
     $/
    0.38
    reel
    0.37
    /*/
    0.37
     >
    0.35
    /$
    0.35
     പല
    0.35
    Act Density 0.010%

    No Known Activations