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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols that indicate structure in text

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

    list numbering and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }}}}
    -0.82
    ]")]
    -0.81
    $}}
    -0.75
    }}},
    -0.70
    }))
    -0.69
     MainAxisSize
    -0.69
    ])))
    -0.66
    )))),
    -0.66
    }")]
    -0.66
    ]})
    -0.63
    POSITIVE LOGITS
    tahui
    0.50
    marginVertical
    0.48
    <h1>
    0.48
     Herbert
    0.47
     Lieber
    0.47
    Portail
    0.46
    حياته
    0.45
    </strong>
    0.44
    wieś
    0.43
     Eriksen
    0.42
    Act Density 0.012%

    No Known Activations