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

    Neuronpedia

    INDEX
    Explanations

    code snippets and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resources
    0.44
     ресурсы
    0.42
     recursos
    0.42
     dios
    0.42
     RESOURCES
    0.41
     risorse
    0.39
    resources
    0.39
     Resources
    0.39
    唕
    0.38
     علیحد
    0.37
    POSITIVE LOGITS
     Bassett
    0.38
     কর্মকর্তা
    0.37
    Power
    0.37
     lure
    0.37
    Push
    0.37
     forcing
    0.37
    Network
    0.36
     Push
    0.36
     stripping
    0.35
    Staff
    0.35
    Act Density 0.001%

    No Known Activations