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

    Neuronpedia

    INDEX
    Explanations

    end of sentence punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _LAST
    -0.07
     Mission
    -0.07
    сон
    -0.07
     below
    -0.07
    Enter
    -0.06
     יכולה
    -0.06
     gratuite
    -0.06
    Texas
    -0.06
    温度
    -0.06
    要有
    -0.06
    POSITIVE LOGITS
    婘
    0.07
     det
    0.07
     Verfüg
    0.06
    .feed
    0.06
    _FAILURE
    0.06
     Sus
    0.06
     farming
    0.06
     Sadly
    0.06
     gây
    0.06
    Pooling
    0.06
    Act Density 0.046%

    No Known Activations