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

    Neuronpedia

    INDEX
    Explanations

    choosing names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BuildConfig
    0.65
    adto
    0.64
    ouilles
    0.63
    embra
    0.62
    億円
    0.62
     leukocytes
    0.62
    पिछ
    0.60
    сты
    0.60
     pluie
    0.60
    滬
    0.59
    POSITIVE LOGITS
     name
    6.02
     names
    5.54
     Name
    5.43
    name
    5.41
    Name
    5.14
     Names
    4.95
     NAME
    4.74
    names
    4.70
    NAME
    4.69
    名称
    4.68
    Act Density 1.813%

    No Known Activations