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

    Neuronpedia

    INDEX
    Explanations

    model generating structured output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    おう
    0.40
    Truthy
    0.37
    Expl
    0.37
    Genre
    0.37
     জ্বাল
    0.37
    НЫ
    0.36
    Perhaps
    0.36
     Genesis
    0.36
    精灵
    0.36
    NuGetPackage
    0.36
    POSITIVE LOGITS
     renovations
    0.41
     hanging
    0.40
     thriving
    0.39
     renovation
    0.39
     transaction
    0.38
     transactions
    0.38
     renovating
    0.38
    吊
    0.37
     worrying
    0.37
     lentils
    0.37
    Act Density 0.053%

    No Known Activations