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

    Neuronpedia

    INDEX
    Explanations

    major spoilers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     அருக
    0.38
    挹
    0.38
     econom
    0.37
    レンチ
    0.37
     oportun
    0.35
     экономической
    0.35
    ਬ
    0.35
     গন
    0.35
    ゑ
    0.35
    ニーズ
    0.34
    POSITIVE LOGITS
     spoiler
    2.48
     spoilers
    2.41
     Spoiler
    2.25
    Spoiler
    2.09
     spoil
    1.90
     spoiling
    1.77
     spoiled
    1.72
    spo
    1.69
    Spo
    1.68
     spoils
    1.65
    Act Density 0.008%

    No Known Activations