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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and special characters

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

    expressions with `&=`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MLLoader
    -1.10
    findpost
    -1.05
    <unused79>
    -1.04
    <unused68>
    -1.04
    <unused16>
    -1.03
    <unused14>
    -1.03
    <unused17>
    -1.03
    <unused23>
    -1.03
    [@BOS@]
    -1.03
    <unused3>
    -1.03
    POSITIVE LOGITS
    2
    0.22
     Sección
    0.22
     con
    0.22
    7
    0.21
     
    0.21
     brand
    0.20
    �
    0.20
    J
    0.19
     тя
    0.19
    1
    0.19
    Act Density 0.132%

    No Known Activations