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

    Neuronpedia

    INDEX
    Explanations

    learning rate assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     informacji
    0.40
     प्रेरणात्मक
    0.39
     ruk
    0.39
    atthakath
    0.39
    rollerskates
    0.38
     NONE
    0.38
     inactivated
    0.37
    鋤
    0.37
    প্রায়
    0.36
    óloga
    0.36
    POSITIVE LOGITS
     symptoms
    0.46
     Symptoms
    0.38
     leak
    0.38
     Leak
    0.37
    =
    0.37
     ver
    0.36
     net
    0.36
     engineer
    0.36
     diagnosis
    0.35
    atsion
    0.35
    Act Density 0.008%

    No Known Activations