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

    Neuronpedia

    INDEX
    Explanations

    between data or entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trimming
    0.72
    正则表达式
    0.70
     joking
    0.70
    技术
    0.68
     reductase
    0.66
     downg
    0.64
    Stderr
    0.64
    水を
    0.64
     arquitet
    0.64
     GridLayout
    0.63
    POSITIVE LOGITS
     data
    1.12
     entities
    1.08
     ентите
    1.07
     variables
    1.07
    variables
    1.05
    data
    1.05
     Data
    0.99
     Entities
    0.99
     variable
    0.96
     entidades
    0.96
    Act Density 1.212%

    No Known Activations