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

    Neuronpedia

    INDEX
    Explanations

    mathematical functions and computations

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

    Mathematical statements with integers or numbers

    np_acts-logits-general · gemini-2.0-flash

    positive integers and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Emer
    -0.51
    ]+=
    -0.51
    Források
    -0.51
     wouldn
    -0.50
     <
    -0.49
    ⇔
    -0.48
    ©
    -0.48
    BagLayout
    -0.47
    worth
    -0.47
    unca
    -0.47
    POSITIVE LOGITS
    +#+#
    0.93
     myſelf
    0.79
     ―――――
    0.79
     quelconque
    0.74
     quelcon
    0.74
    ſelf
    0.70
     Anſ
    0.68
     auffi
    0.67
    PhysRevD
    0.67
     fiscale
    0.66
    Act Density 1.563%

    No Known Activations