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

    Neuronpedia

    INDEX
    Explanations

    recommend or return

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Later
    0.83
     Later
    0.72
     later
    0.72
     senere
    0.71
     അല്ല
    0.70
     successive
    0.70
     איך
    0.69
    どうぞ
    0.69
     postérieures
    0.69
    וג
    0.69
    POSITIVE LOGITS
     return
    0.89
     będzie
    0.79
     purchase
    0.78
    return
    0.76
     returning
    0.74
     buy
    0.71
     patron
    0.70
    तमंद
    0.70
     encontrará
    0.68
     będ
    0.68
    Act Density 0.001%

    No Known Activations