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

    Neuronpedia

    INDEX
    Explanations

    time units ago

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     последу
    0.74
    ສຸດ
    0.70
     주변
    0.67
    ছন
    0.67
    ufth
    0.67
    られます
    0.67
    credentials
    0.67
    next
    0.66
    streamlit
    0.65
    埝
    0.65
    POSITIVE LOGITS
     ago
    3.01
     Ago
    2.32
     ag
    2.31
    ago
    2.26
    Ago
    2.06
     AGO
    2.06
     Ag
    2.03
    AGO
    2.03
    Ag
    1.94
    ag
    1.77
    Act Density 0.026%

    No Known Activations