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

    Neuronpedia

    INDEX
    Explanations

    Se centra en, se basa en

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     leveraging
    0.83
     choosing
    0.81
     noting
    0.77
     examining
    0.74
     putting
    0.73
     removing
    0.73
     adding
    0.71
     letting
    0.70
     adjusting
    0.70
     forgetting
    0.70
    POSITIVE LOGITS
     occurs
    1.90
     имеет
    1.85
     является
    1.81
     constitutes
    1.77
     tiene
    1.76
     είναι
    1.75
     دارد
    1.73
     represents
    1.73
     contiene
    1.72
     contains
    1.71
    Act Density 0.211%

    No Known Activations