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

    Neuronpedia

    INDEX
    Explanations

    phrases in lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pathophys
    0.27
     powertrain
    0.23
     virulent
    0.23
     astrophysical
    0.23
     supabase
    0.23
     supersymmetric
    0.23
     cannabin
    0.22
    🗾
    0.21
    |</
    0.21
     partake
    0.21
    POSITIVE LOGITS
     जानिए
    0.24
     G
    0.23
    S
    0.22
     walang
    0.21
    L
    0.21
    K
    0.21
     няма
    0.21
     केवल
    0.20
     S
    0.20
     keine
    0.20
    Act Density 0.352%

    No Known Activations