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

    Neuronpedia

    INDEX
    Explanations

    explaining specific details to someone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᴇ
    1.48
     elevar
    1.35
    急性
    1.30
    nombre
    1.29
     procé
    1.28
    émor
    1.26
    𝖐
    1.22
    ню
    1.22
    inflammation
    1.21
    िंग
    1.21
    POSITIVE LOGITS
    ührt
    1.01
    bigskip
    0.96
    地図
    0.93
     specific
    0.92
    ست
    0.92
     distinctions
    0.91
    ்ட்
    0.91
    ദന
    0.91
     Spanish
    0.90
     quaint
    0.89
    Act Density 0.001%

    No Known Activations