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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas and relationships involving variables and their interactions

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

    Superscript citations

    np_acts-logits-general · gemini-2.0-flash

    closing delimiters like ')}' and '}'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.67
    WebControls
    -0.66
    $(
    -0.64
    BeginContext
    -0.62
     GenerationType
    -0.60
     سكانية
    -0.59
     ExecuteAsync
    -0.58
    Identyfik
    -0.58
     Complaint
    -0.58
    $?
    -0.56
    POSITIVE LOGITS
    )}$
    0.95
    ]}$
    0.86
     \%}$
    0.78
    )}$,
    0.71
     )}$
    0.67
    </sub>
    0.66
    )}$.
    0.65
    })}$
    0.63
    *}$
    0.61
    }$)
    0.58
    Act Density 0.626%

    No Known Activations