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

    Neuronpedia

    INDEX
    Explanations

    list items in lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beh
    0.70
     Fer
    0.65
    เมื่อ
    0.65
     ket
    0.62
     té
    0.60
    há
    0.58
     nær
    0.58
     Legacy
    0.58
     faz
    0.58
     nev
    0.57
    POSITIVE LOGITS
    Dome
    0.76
     Dubey
    0.66
    countdown
    0.66
     ازيكم
    0.66
    CRM
    0.65
     કાર્ડ
    0.65
    ږئ
    0.65
    őbb
    0.64
    দীন
    0.64
     councillors
    0.63
    Act Density 0.012%

    No Known Activations