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

    Neuronpedia

    INDEX
    Explanations

    identifying "name" fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝙙
    0.41
    ැ
    0.37
     jeweiligen
    0.37
     கிடைக்க
    0.37
     Edmond
    0.36
    ာ
    0.35
    𝗿
    0.35
     کە
    0.35
    罅
    0.35
    옥
    0.35
    POSITIVE LOGITS
    modelVersion
    0.56
     name
    0.47
     Nombre
    0.46
    xmlns
    0.45
    name
    0.43
     general
    0.43
     nombre
    0.43
    General
    0.42
     inherited
    0.42
     Name
    0.41
    Act Density 0.012%

    No Known Activations