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

    Neuronpedia

    INDEX
    Explanations

    defining rules and guidelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mobs
    0.32
     experiment
    0.32
     installments
    0.30
     entityManager
    0.30
     instalments
    0.30
     supernatant
    0.29
     watery
    0.29
     detections
    0.29
     hordes
    0.29
     sportsmen
    0.29
    POSITIVE LOGITS
     recommends
    0.44
    Guidelines
    0.43
     prevede
    0.41
     guidelines
    0.40
     Guidelines
    0.40
     suggests
    0.38
     рекоменду
    0.37
     предусматри
    0.37
    says
    0.36
     defines
    0.36
    Act Density 0.197%

    No Known Activations