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

    Neuronpedia

    INDEX
    Explanations

    phase, date, discovered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    carbon
    0.85
    क्ट
    0.84
    pineapple
    0.81
    defines
    0.79
     adheres
    0.79
     absorbs
    0.78
    ⊹
    0.78
    becomes
    0.77
     Bastian
    0.77
    mutable
    0.76
    POSITIVE LOGITS
     kör
    0.75
    ür
    0.70
    änner
    0.70
     Ö
    0.68
    ્રે
    0.68
     беше
    0.68
    ål
    0.67
     laureate
    0.66
    ïde
    0.65
    TOUCH
    0.64
    Act Density 0.002%

    No Known Activations