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

    Neuronpedia

    INDEX
    Explanations

    places and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KindOfClass
    0.42
    的的
    0.40
    Pojo
    0.39
     зво
    0.38
     వరు
    0.36
    Narc
    0.36
     sürekli
    0.36
    ork
    0.36
     Continuous
    0.35
    geld
    0.35
    POSITIVE LOGITS
    英雄
    0.35
    4
    0.34
    ن
    0.34
     sconf
    0.34
    ничный
    0.33
    і
    0.33
    ვნ
    0.32
    ní
    0.32
    ulte
    0.32
    nea
    0.31
    Act Density 0.002%

    No Known Activations