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

    Neuronpedia

    INDEX
    Explanations

    likes and engagement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hauer
    0.38
    dest
    0.36
    buri
    0.36
    釟
    0.35
    قتص
    0.35
     extr
    0.34
    জার
    0.34
    daf
    0.34
    朩
    0.33
    psz
    0.33
    POSITIVE LOGITS
     likes
    1.93
     Likes
    1.85
    Likes
    1.76
    likes
    1.69
     liking
    1.66
     liked
    1.63
     लाइक
    1.54
     좋아요
    1.47
    liked
    1.44
    Liked
    1.41
    Act Density 0.013%

    No Known Activations