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

    Neuronpedia

    INDEX
    Explanations

    patterns or structures in mathematical expressions involving parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    LaTeX math variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mouseClicked
    -0.47
     Vex
    -0.43
    MessageTagHelper
    -0.41
    dì
    -0.40
    ReusableCell
    -0.40
     سعر
    -0.39
     besti
    -0.38
    rde
    -0.38
     Indo
    -0.38
    engesch
    -0.38
    POSITIVE LOGITS
     آن
    1.73
    آن
    1.30
     اون
    0.92
     daquele
    0.67
     them
    0.66
     آنها
    0.66
     ProtoMessage
    0.65
     Оно
    0.64
     它
    0.63
     those
    0.63
    Act Density 0.001%

    No Known Activations