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

    Neuronpedia

    INDEX
    Explanations

    company, Pip

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kwik
    1.65
     %}
    1.62
     election
    1.61
     DataTable
    1.61
     Scribner
    1.60
     haemorrh
    1.58
    }}]
    1.57
     circumcision
    1.55
    }:=
    1.54
    ヨン
    1.54
    POSITIVE LOGITS
    采集
    1.87
     меч
    1.66
     meravigli
    1.62
     sepeda
    1.60
    探索
    1.57
     effectué
    1.56
    Solo
    1.54
     маршру
    1.51
     regreso
    1.49
    iendo
    1.48
    Act Density 0.219%

    No Known Activations