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

    Neuronpedia

    INDEX
    Explanations

    concepts related to foundational assumptions

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

    assuming CAR

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     at
    -0.24
    (['
    -0.23
    /
    -0.23
     formie
    -0.23
     –
    -0.22
    A
    -0.21
    Key
    -0.21
    :
    -0.21
     can
    -0.21
    capai
    -0.21
    POSITIVE LOGITS
    ########.
    10.44
    :+:
    2.25
    libft
    2.16
     surla
    1.48
     kasarigan
    1.44
    #+#
    1.43
    +#+
    1.41
     AssemblyCulture
    1.40
     المعيارى
    1.35
    +#+#
    1.32
    Act Density 0.000%

    No Known Activations