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

    Neuronpedia

    INDEX
    Explanations

    common birds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     crocodile
    0.76
     Crocodile
    0.75
     aHUS
    0.69
     Lotus
    0.67
     seabed
    0.65
    Monster
    0.65
     crocodiles
    0.65
    槤
    0.65
     Weapons
    0.64
     werewolf
    0.62
    POSITIVE LOGITS
     song
    1.39
     robin
    1.31
     Song
    1.23
     Cardinals
    1.20
     cardinals
    1.17
     sparrow
    1.10
    Song
    1.09
     birds
    1.07
    robin
    1.06
     songs
    1.06
    Act Density 0.043%

    No Known Activations