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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notation related to functions and transformations

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

    absolute value notation with Greek letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BrowserRouter
    -0.55
    BrowserRouter
    -0.53
    SetName
    -0.45
     immobilier
    -0.45
    Getenv
    -0.44
     Tela
    -0.41
    chalet
    -0.41
     Weich
    -0.40
    Sant
    -0.40
    存于互联网档案馆
    -0.40
    POSITIVE LOGITS
    |\
    1.56
    |-
    1.16
    |_
    1.15
     $|\
    1.13
     |\
    1.09
    |:
    1.01
    |/
    1.01
    |'
    1.01
    }|\
    0.99
    |$
    0.98
    Act Density 0.018%

    No Known Activations