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

    Neuronpedia

    INDEX
    Explanations

    long-term plan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     subjekt
    0.59
    जेक्शन
    0.59
     particle
    0.59
     истины
    0.58
     tượng
    0.58
    iseconds
    0.57
     particles
    0.57
    বয়
    0.57
     запя
    0.57
    adă
    0.57
    POSITIVE LOGITS
     plan
    5.33
     Plan
    5.03
     plans
    5.02
    Plan
    4.96
     planning
    4.94
    plan
    4.84
     Plans
    4.75
     Planning
    4.68
    Planning
    4.60
    planning
    4.54
    Act Density 0.815%

    No Known Activations