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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gps
    -0.07
    -su
    -0.07
    סיר
    -0.07
    ╙
    -0.07
     đự
    -0.07
    횰
    -0.06
     Legislation
    -0.06
     distinguishing
    -0.06
    icions
    -0.06
    Monitor
    -0.06
    POSITIVE LOGITS
     Bram
    0.07
     $('#'
    0.07
     {$
    0.07
    不够
    0.07
    攻
    0.07
    样板
    0.07
    <S
    0.07
    <User
    0.06
    [row
    0.06
    (false
    0.06
    Act Density 0.023%

    No Known Activations