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

    Neuronpedia

    INDEX
    Explanations

    definitions and acronyms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prequel
    0.47
     discoveries
    0.41
     બિ
    0.40
     NEXT
    0.38
    itone
    0.37
     bait
    0.37
     smoky
    0.37
    拿出
    0.37
    汽
    0.37
     parton
    0.37
    POSITIVE LOGITS
    जना
    0.39
    ISC
    0.39
    រស
    0.38
    Password
    0.38
    試料
    0.37
    InData
    0.37
    Scientific
    0.36
    ದುಕೊಳ್ಳ
    0.36
     وابسته
    0.36
    Information
    0.36
    Act Density 0.013%

    No Known Activations