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

    Neuronpedia

    INDEX
    Explanations

    get started doing something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.71
    r
    0.68
    ب
    0.65
    人气
    0.63
    lash
    0.61
    sided
    0.61
    ly
    0.60
    sama
    0.60
     geschikt
    0.60
    یت
    0.60
    POSITIVE LOGITS
     Стаўкі
    0.69
    ɪ
    0.65
     vagas
    0.62
     коюм
    0.62
    ㎜
    0.62
     wildfires
    0.62
     tantos
    0.62
     runways
    0.62
     ἐ
    0.61
    ゥム
    0.60
    Act Density 0.156%

    No Known Activations