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

    Neuronpedia

    INDEX
    Explanations

    web content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     मुह
    0.45
     Churchill
    0.41
    culaire
    0.41
    ໂ
    0.41
     Muhammad
    0.40
     Darcy
    0.40
    ഠ
    0.40
    Ϻ
    0.39
    Say
    0.39
    Ҷ
    0.39
    POSITIVE LOGITS
    web
    0.41
    router
    0.39
     relationship
    0.38
     web
    0.38
    ப்பட்டது
    0.37
    喧
    0.37
     vzt
    0.37
     tweeter
    0.36
    relationship
    0.36
     nuanced
    0.36
    Act Density 0.002%

    No Known Activations