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

    Neuronpedia

    INDEX
    Explanations

    outlining a plan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    技术的
    0.44
     Comparisons
    0.38
    方便
    0.38
    ivatives
    0.38
    目的
    0.38
    环境中
    0.37
     길이가
    0.37
     خاصيه
    0.37
    特点
    0.36
     کاس
    0.35
    POSITIVE LOGITS
     plan
    2.19
    plan
    1.85
     плана
    1.76
     план
    1.75
    计划
    1.65
     plans
    1.62
     Plan
    1.60
     rencana
    1.60
    Plan
    1.59
     plán
    1.59
    Act Density 0.234%

    No Known Activations