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

    Neuronpedia

    INDEX
    Explanations

    certain words or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MRD
    0.77
     Messiah
    0.74
     tosses
    0.73
     standen
    0.73
     interess
    0.72
     seemed
    0.72
     seem
    0.72
     interessa
    0.71
     complacent
    0.71
     Alek
    0.70
    POSITIVE LOGITS
    ibt
    0.76
    no
    0.75
    ibel
    0.74
    No
    0.72
    Tile
    0.72
    mod
    0.71
    onym
    0.70
     மக்கள்
    0.70
    Be
    0.70
    Ab
    0.69
    Act Density 0.000%

    No Known Activations