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

    Neuronpedia

    INDEX
    Explanations

    what is allowed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    제의
    0.40
     പ്രതീ
    0.39
     inkább
    0.39
    ומ
    0.38
     painstakingly
    0.38
     നന്ന
    0.38
    ጠን
    0.37
     notorious
    0.37
     গুজব
    0.36
    巅
    0.36
    POSITIVE LOGITS
     legally
    1.00
     permissible
    1.00
     allowed
    0.96
     boleh
    0.95
     lawfully
    0.91
     freely
    0.89
     allowable
    0.87
     permitted
    0.86
     librement
    0.81
     darf
    0.80
    Act Density 0.059%

    No Known Activations