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

    Neuronpedia

    INDEX
    Explanations

    Wikipedia references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝑫
    2.41
    𝑪
    2.39
    Ну
    2.38
     Tagen
    2.33
     unforeseen
    2.33
    𝒅
    2.32
    人士
    2.32
    μού
    2.30
     exacerb
    2.27
    ुप
    2.27
    POSITIVE LOGITS
    ли
    3.07
    er
    2.88
     ćete
    2.77
    いきます
    2.75
    ০
    2.69
    ר
    2.67
    জমেন্ট
    2.65
     Lordships
    2.62
    meyer
    2.60
    ிறது
    2.56
    Act Density 0.005%

    No Known Activations