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

    Neuronpedia

    INDEX
    Explanations

    Ruby code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getRepository
    0.41
    Flor
    0.40
    骧
    0.39
    şen
    0.39
    Какие
    0.38
    Seeds
    0.37
    ayın
    0.37
    வற்ற
    0.36
    ческие
    0.36
    Lu
    0.36
    POSITIVE LOGITS
     Sensitivity
    0.43
     Civilian
    0.43
     Conjug
    0.41
     l
    0.40
     cam
    0.38
     vertex
    0.38
     blotting
    0.38
     sym
    0.38
     Integer
    0.38
     Recognition
    0.38
    Act Density 0.004%

    No Known Activations