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

    Neuronpedia

    INDEX
    Explanations

    all the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mapping
    0.38
    ዊ
    0.38
     grammaticality
    0.37
     reconoce
    0.36
    ട്ടുണ്ട്
    0.35
    monia
    0.35
     biologist
    0.35
    Simulation
    0.35
    ಶ್
    0.34
    hope
    0.34
    POSITIVE LOGITS
     rosem
    0.41
     editions
    0.40
     प्रत
    0.39
     commute
    0.38
    Ut
    0.37
     edição
    0.37
     ende
    0.37
     Messrs
    0.37
     Segu
    0.37
     retain
    0.37
    Act Density 0.000%

    No Known Activations