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

    Neuronpedia

    INDEX
    Explanations

    request

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🫐
    0.38
    ໊
    0.38
    🫰
    0.36
    ⃞
    0.36
    ໋
    0.35
    彡
    0.34
    ELEASE
    0.34
    🫡
    0.34
    🫤
    0.34
     latitudine
    0.33
    POSITIVE LOGITS
     Chapter
    0.43
     chapter
    0.43
     What
    0.38
     CHAPTER
    0.38
    Chapter
    0.37
    europa
    0.36
    CHAPTER
    0.35
     Rhet
    0.35
    chapter
    0.35
    What
    0.33
    Act Density 0.000%

    No Known Activations