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

    Neuronpedia

    INDEX
    Explanations

    place names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cabin
    0.86
     Garage
    0.82
    jaya
    0.81
     Firewall
    0.80
     House
    0.80
     page
    0.78
     definition
    0.77
     Chamber
    0.76
    orado
    0.76
     Hammond
    0.75
    POSITIVE LOGITS
    تم
    0.92
    έ
    0.86
    स
    0.79
    ที่มี
    0.78
    си
    0.76
     पू
    0.75
     Vieni
    0.75
    ሥ
    0.75
    डब्ल्यू
    0.74
    αι
    0.73
    Act Density 0.000%

    No Known Activations