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

    Neuronpedia

    INDEX
    Explanations

    couple of, through, chatbot, house lease, decided on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    l
    0.98
    s
    0.89
    م
    0.82
    ਆਂ
    0.82
    KYO
    0.80
    p
    0.80
    с
    0.79
    ıları
    0.78
    س
    0.78
    ل
    0.77
    POSITIVE LOGITS
     deformations
    0.98
    実は
    0.81
     quím
    0.79
    rechts
    0.79
    生態
    0.76
    諡
    0.75
     beasts
    0.75
     lotions
    0.75
     lekin
    0.73
     detonations
    0.73
    Act Density 0.001%

    No Known Activations