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

    Neuronpedia

    INDEX
    Explanations

    numbers and counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bowl
    0.70
    Upgrade
    0.60
    script
    0.56
     watchlist
    0.56
    bowl
    0.56
    algorithm
    0.55
    albumin
    0.55
    Rez
    0.55
    Playlist
    0.54
    Fleet
    0.54
    POSITIVE LOGITS
     items
    1.21
     개의
    1.16
     pieces
    1.15
    개의
    1.08
     consecutive
    1.06
     identical
    0.99
     syllables
    0.98
     vials
    0.96
     itens
    0.95
     vertices
    0.93
    Act Density 0.424%

    No Known Activations