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

    Neuronpedia

    INDEX
    Explanations

    cognitive dissonance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prestigious
    1.22
     userService
    1.07
     suspicious
    1.06
    兵庫
    1.06
     userRepository
    1.06
     multiplayer
    1.05
    পিত
    1.03
    strlen
    1.02
    gzip
    1.01
     waypoint
    1.01
    POSITIVE LOGITS
    lu
    1.22
    臾
    1.15
    <%=
    1.10
    liefer
    1.04
    𝘈
    1.03
    ्स
    1.02
     Zá
    0.99
     vypl
    0.99
    itä
    0.97
    ャ
    0.96
    Act Density 0.004%

    No Known Activations