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

    Neuronpedia

    INDEX
    Explanations

    conspiracy theory,supports,effectiveness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    枱
    0.57
    ಾಯಿ
    0.54
    ServiceGroupID
    0.50
    یی
    0.50
    0.50
     benchmarks
    0.49
    ंजय
    0.48
     ignition
    0.47
    カイブ
    0.47
    ignition
    0.46
    POSITIVE LOGITS
    (
    0.49
    idée
    0.45
    เลย
    0.45
     Insta
    0.42
     veut
    0.42
    icius
    0.41
    ud
    0.41
     اصل
    0.40
    aced
    0.40
     zacz
    0.40
    Act Density 0.012%

    No Known Activations