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

    Neuronpedia

    INDEX
    Explanations

    consistency is key

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     затра
    0.55
    UARY
    0.54
     проде
    0.52
     घड
    0.49
     食器
    0.48
     обви
    0.47
    แมนเชสเตอร์
    0.46
    cı
    0.46
     сосу
    0.46
    റ്റു
    0.46
    POSITIVE LOGITS
     s
    0.43
     Botanical
    0.43
    transition
    0.41
     viral
    0.40
     very
    0.40
     latter
    0.40
     freestyle
    0.40
     land
    0.40
     hits
    0.40
    mu
    0.40
    Act Density 0.005%

    No Known Activations