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

    Neuronpedia

    INDEX
    Explanations

    periods of time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Approximately
    0.42
     HAL
    0.37
     Hal
    0.37
     Taro
    0.37
     src
    0.36
    asso
    0.36
    osti
    0.36
     Kant
    0.35
     Statement
    0.35
     Soon
    0.35
    POSITIVE LOGITS
    甚至
    0.78
    甚至是
    0.71
     thậm
    0.63
     hatta
    0.62
    乃至
    0.61
     tens
    0.60
     thousands
    0.59
     hundreds
    0.59
    lerce
    0.57
     এমনকি
    0.55
    Act Density 0.029%

    No Known Activations