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

    Neuronpedia

    INDEX
    Explanations

    programming constants and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lím
    0.45
     Single
    0.39
     ट्रायंगल
    0.39
     Zero
    0.38
     Wix
    0.37
     Radioactive
    0.37
     wx
    0.37
     Thats
    0.37
    WithOptions
    0.36
     yên
    0.36
    POSITIVE LOGITS
    QUESTION
    0.44
    javac
    0.39
    TRUST
    0.39
    oris
    0.37
     QUESTION
    0.36
     FAMILY
    0.36
    Ellis
    0.36
    RESOL
    0.36
    オー
    0.35
    CHAPTER
    0.35
    Act Density 0.001%

    No Known Activations