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

    Neuronpedia

    INDEX
    Explanations

    save or saving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    颛
    0.71
    Brid
    0.62
     fragilis
    0.61
    ducible
    0.61
     मुखर्जी
    0.60
     Juillet
    0.59
    ingular
    0.59
    йы
    0.58
     اجيب
    0.58
    ணற
    0.57
    POSITIVE LOGITS
     save
    4.77
     saving
    4.74
     Save
    4.60
     saves
    4.49
     saved
    4.48
    Save
    4.48
    save
    4.42
     Saving
    4.32
    Saving
    4.15
    saving
    4.04
    Act Density 0.526%

    No Known Activations