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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ११
    0.76
     eight
    0.66
    0.66
     sixteen
    0.65
     fourteen
    0.64
    十四
    0.63
    HomeScreen
    0.62
    Jamaica
    0.62
    ८
    0.61
     oito
    0.61
    POSITIVE LOGITS
     resorts
    0.73
    ponents
    0.72
     وړ
    0.71
     deutsch
    0.70
     எவ்வாறு
    0.70
    谓
    0.69
    ম্ভ
    0.69
    hipster
    0.69
    緘
    0.67
     মশ
    0.67
    Act Density 0.006%

    No Known Activations