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

    Neuronpedia

    INDEX
    Explanations

    youtube.com domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chast
    0.70
    ahr
    0.70
    alle
    0.66
     Sprague
    0.65
     পঞ্চ
    0.65
    忻
    0.65
     Abt
    0.64
     -------------
    0.64
     ग्रे
    0.64
    ustus
    0.63
    POSITIVE LOGITS
     Com
    1.02
     Comet
    1.02
    Wow
    1.01
     Wink
    0.96
     Romance
    0.95
     Wow
    0.94
    Romantic
    0.94
     WOW
    0.92
     Glam
    0.91
    COM
    0.91
    Act Density 0.114%

    No Known Activations