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

    Neuronpedia

    INDEX
    Explanations

    instances of various symbols or formatting marks

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

    italics or emphasis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.82
    IVEREF
    -0.82
    पया
    -0.79
     Administrativna
    -0.75
     EconPapers
    -0.73
    principalColumn
    -0.68
     وتسجيلات
    -0.66
     ब्रेकडाउन
    -0.65
    #+#
    -0.65
    yarnpkg
    -0.64
    POSITIVE LOGITS
    antaranya
    0.48
    rceil
    0.45
    </i>
    0.44
     oluyor
    0.42
    '}}
    0.40
    </em>
    0.40
     =
    0.39
    absch
    0.37
     olsun
    0.37
    ]")]
    0.37
    Act Density 0.337%

    No Known Activations