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

    Neuronpedia

    INDEX
    Explanations

    likes and comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    কাঁ
    0.77
    ঠে
    0.74
     специ
    0.70
     prélim
    0.67
     παρου
    0.67
    товых
    0.65
    াপনের
    0.64
    Ӏ
    0.64
     romanzo
    0.63
    ériences
    0.63
    POSITIVE LOGITS
    Likes
    1.84
     Likes
    1.83
     likes
    1.80
     liked
    1.73
    likes
    1.73
     liking
    1.69
     comment
    1.69
     Comment
    1.67
    Comment
    1.65
    comments
    1.64
    Act Density 0.127%

    No Known Activations