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

    Neuronpedia

    INDEX
    Explanations

    here's a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     covering
    0.56
     Covering
    0.54
     COVER
    0.54
     covers
    0.53
     covered
    0.52
    covering
    0.52
    covers
    0.51
     پوش
    0.51
     cover
    0.51
     cubrir
    0.51
    POSITIVE LOGITS
     breakdown
    2.00
     Breakdown
    1.87
    Break
    1.78
     breakdowns
    1.74
     breakup
    1.63
     break
    1.59
    break
    1.59
     Break
    1.58
     BREAK
    1.48
     ब्रेक
    1.45
    Act Density 0.303%

    No Known Activations