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

    Neuronpedia

    INDEX
    Explanations

    entity names and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     coastline
    0.43
    six
    0.41
    moor
    0.40
    range
    0.40
    leece
    0.40
     pumps
    0.39
    bounds
    0.39
     liquids
    0.39
    surgeon
    0.39
    MHz
    0.38
    POSITIVE LOGITS
     plural
    0.50
     name
    0.46
    ชื่อ
    0.45
    tablename
    0.43
    Classe
    0.41
    类
    0.41
     noun
    0.41
     classy
    0.41
     Heading
    0.40
    เรียก
    0.40
    Act Density 0.039%

    No Known Activations