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

    Neuronpedia

    INDEX
    Explanations

    taking action or responsibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     détecter
    0.47
     بحيث
    0.40
    ᥣ
    0.38
    中です
    0.38
    改
    0.37
     worsened
    0.37
    竣
    0.37
     verlassen
    0.36
     détect
    0.35
    щі
    0.35
    POSITIVE LOGITS
     honours
    0.52
     Honours
    0.50
     licences
    0.50
    aboard
    0.48
     প্রয়োজনীয়
    0.47
     fertilisers
    0.47
     organisations
    0.45
     onboard
    0.45
     tyres
    0.45
     rumours
    0.45
    Act Density 0.001%

    No Known Activations