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

    Neuronpedia

    INDEX
    Explanations

    AI assistant introductions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TEA
    0.39
    LetterGrade
    0.38
    insertCell
    0.38
     gamanam
    0.37
    Estate
    0.37
    Clos
    0.37
    TestMethod
    0.37
    찹
    0.37
    Innovation
    0.37
    Vehicle
    0.37
    POSITIVE LOGITS
     stretched
    0.40
     roller
    0.39
     pretty
    0.39
     stretches
    0.39
     impre
    0.38
    pretty
    0.38
     ø
    0.36
     अर्जेंटीना
    0.36
     efectivos
    0.36
     ny
    0.35
    Act Density 0.002%

    No Known Activations