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

    Neuronpedia

    INDEX
    Explanations

    causation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    உலகின்
    0.88
    itory
    0.87
    တိ
    0.86
    tis
    0.86
     حنا
    0.82
    i
    0.80
    agen
    0.80
    Bet
    0.79
    atio
    0.79
    Pais
    0.78
    POSITIVE LOGITS
     decisions
    0.99
    들과
    0.91
     demand
    0.85
    化学
    0.83
     part
    0.83
    因素
    0.82
    的需求
    0.81
    력을
    0.80
    歓
    0.80
    股价
    0.80
    Act Density 0.074%

    No Known Activations