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

    Neuronpedia

    INDEX
    Explanations

    financial symbols and values

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

    bracketed expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tembelea
    -0.77
    AnimationsModule
    -0.67
    AccessorTable
    -0.66
    styleType
    -0.65
    CloseOperation
    -0.60
    原始内容存档于
    -0.58
    GOTREF
    -0.57
     AssemblyCompany
    -0.57
    ingtones
    -0.56
    yarnpkg
    -0.56
    POSITIVE LOGITS
    $
    0.81
    <bos>
    0.80
    }$
    0.69
    }}$
    0.65
    ]}$
    0.65
    $)$
    0.64
     }}$
    0.63
    })$
    0.62
    ]$
    0.61
    }]$
    0.61
    Act Density 0.145%

    No Known Activations