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

    Neuronpedia

    INDEX
    Explanations

    keywords, tags, or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    0.48
    コン
    0.45
    /_
    0.41
    ylmethylsulfanyl
    0.41
     コン
    0.40
    /-
    0.39
     Architektur
    0.38
     весьма
    0.38
     சில
    0.37
     (
    0.37
    POSITIVE LOGITS
    Featured
    0.43
     ACLU
    0.42
    负担
    0.39
     adresu
    0.38
    featured
    0.37
     governo
    0.37
    իտ
    0.37
     regering
    0.36
    电视剧
    0.36
     bedrijven
    0.36
    Act Density 0.014%

    No Known Activations