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

    Neuronpedia

    INDEX
    Explanations

    keywords and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Land
    0.57
     outfitted
    0.53
     truck
    0.50
    REGI
    0.50
     Nagpur
    0.49
     nationwide
    0.48
     Rehab
    0.48
     Truck
    0.48
    Ga
    0.47
     choose
    0.47
    POSITIVE LOGITS
    借助
    0.45
    branding
    0.43
    producto
    0.41
    ᕋ
    0.40
    genres
    0.40
    列表
    0.40
    stdlib
    0.40
    覀
    0.39
    iencia
    0.39
    ленном
    0.39
    Act Density 0.003%

    No Known Activations