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

    Neuronpedia

    INDEX
    Explanations

    parentheses and related mathematical notation

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

    Mathematical or code expressions with parentheses

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions with parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dol
    -0.54
    (
    -0.53
    ers
    -0.51
     hel
    -0.50
     vel
    -0.49
     past
    -0.48
    -0.48
     Bran
    -0.48
     pan
    -0.47
    ese
    -0.47
    POSITIVE LOGITS
     referenties
    1.13
    }))

    0.93
    }))
    0.92
    })]
    0.91
    adaptiveStyles
    0.91
    "]}
    0.89
    "]))
    0.85
    sizeCache
    0.83
    ]")]
    0.83
    ])]
    0.83
    Act Density 0.834%
    No Known Activations