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

    Neuronpedia

    INDEX
    Explanations

    measured quantities or indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    伈
    0.42
     Discipl
    0.40
     Selección
    0.40
     Skills
    0.40
    轵
    0.40
     учун
    0.40
     دلچ
    0.39
    Skills
    0.39
     Organ
    0.38
     सीखते
    0.38
    POSITIVE LOGITS
     index
    0.65
     measured
    0.64
     indices
    0.62
     indexes
    0.60
     proxies
    0.58
    index
    0.58
    measured
    0.58
     quantified
    0.58
     индекс
    0.57
     measures
    0.56
    Act Density 0.040%

    No Known Activations