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

    Neuronpedia

    INDEX
    Explanations

    internal analysis; company values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chemo
    0.42
     metal
    0.41
     question
    0.39
     aryl
    0.39
     sop
    0.38
     thaw
    0.38
     gato
    0.38
    0.38
    Collins
    0.38
    third
    0.38
    POSITIVE LOGITS
    YEAR
    0.47
     имеет
    0.46
     достоин
    0.46
    ainkan
    0.46
    羢
    0.46
     histórico
    0.45
    ionar
    0.45
    irement
    0.45
    年
    0.45
    ০০
    0.45
    Act Density 0.004%

    No Known Activations