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

    Neuronpedia

    INDEX
    Explanations

    explodes and unfolds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     사용하는
    0.73
     verwenden
    0.64
    Removing
    0.61
     आहोत
    0.61
     ہیں
    0.59
     हूँ
    0.59
     باشند
    0.58
     사용할
    0.57
     använda
    0.57
    Removal
    0.57
    POSITIVE LOGITS
     unfolds
    1.13
     begins
    1.11
     comes
    1.04
     emerges
    1.02
     evolves
    1.00
     rises
    0.99
     blossomed
    0.98
     arises
    0.97
     goes
    0.94
     ensues
    0.93
    Act Density 0.573%

    No Known Activations