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

    Neuronpedia

    INDEX
    Explanations

    ai disclaimers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    note
    1.02
     note
    0.82
    Note
    0.80
    credibly
    0.75
     obič
    0.73
     उल्लेखनीय
    0.73
    rict
    0.73
    notes
    0.72
    videmment
    0.71
    因为
    0.71
    POSITIVE LOGITS
     If
    1.15
     Also
    1.09
     My
    1.05
     Above
    1.02
     以上
    0.96
     Pokud
    0.96
     Hopefully
    0.95
     위의
    0.95
     Everyone
    0.94
     Additionally
    0.94
    Act Density 0.034%

    No Known Activations