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

    Neuronpedia

    INDEX
    Explanations

    collect it, ftp =

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hanuman
    0.47
     Chestnut
    0.43
    Spawn
    0.43
     spaw
    0.43
     Hinweis
    0.42
     Spawn
    0.42
     डाक
    0.42
     Ones
    0.42
     Highway
    0.41
     McDonalds
    0.41
    POSITIVE LOGITS
     고려
    0.43
     indes
    0.43
    нь
    0.42
    ья
    0.41
     حاضر
    0.41
    jane
    0.41
    素
    0.40
     metabol
    0.40
    трен
    0.39
    zył
    0.39
    Act Density 3.555%

    No Known Activations