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

    Neuronpedia

    INDEX
    Explanations

    supply line or chain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ين
    1.99
    نا
    1.90
    い
    1.70
    lø
    1.66
    ول
    1.66
    ट्टर
    1.63
    ൈ
    1.63
    inė
    1.61
    פר
    1.59
     sadistic
    1.56
    POSITIVE LOGITS
     найд
    2.02
    tokens
    2.00
     fournis
    1.98
     Supply
    1.95
     dirigés
    1.92
     Materi
    1.88
    2
    1.87
     direta
    1.84
     organiques
    1.83
    ции
    1.81
    Act Density 0.031%

    No Known Activations