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

    Neuronpedia

    INDEX
    Explanations

    bowling activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alanı
    1.11
     pored
    1.05
     alright
    0.98
    涂
    0.97
     aktive
    0.96
     '*')
    0.95
    পত্র
    0.94
     heard
    0.93
    ন্যা
    0.93
     talked
    0.92
    POSITIVE LOGITS
     Kirkpatrick
    1.00
     mesons
    0.89
    contrib
    0.87
     reincarnation
    0.82
    Dinner
    0.82
     Sebagai
    0.81
    pairwise
    0.81
    মায়
    0.80
    Bulk
    0.80
     повышения
    0.80
    Act Density 0.004%

    No Known Activations