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

    Neuronpedia

    INDEX
    Explanations

    instagram urls or content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ږد
    0.41
     "$(
    0.39
     pj
    0.39
     aba
    0.38
     MARK
    0.38
    ประก
    0.38
    ূন্য
    0.37
     PCE
    0.37
     अपील
    0.36
    irk
    0.36
    POSITIVE LOGITS
     reels
    0.66
     reel
    0.64
     Reel
    0.63
    reel
    0.59
     Reels
    0.57
     reeling
    0.52
    tumblr
    0.42
    SCs
    0.39
    scrollTop
    0.38
    stories
    0.38
    Act Density 0.000%

    No Known Activations