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

    Neuronpedia

    INDEX
    Explanations

    references to code structures or snippets in programming contexts

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

    code delimiters and paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.71
    帖最后由
    -0.69
     BoxDecoration
    -0.63
     ivelany
    -0.61
    principalColumn
    -0.60
    OCCURRED
    -0.57
     CreateTagHelper
    -0.57
     InputDecoration
    -0.56
     мәкал
    -0.55
    PerformLayout
    -0.54
    POSITIVE LOGITS
    >
    1.02
    ]>
    0.84
    '>
    0.82
    )}>
    0.81
    }>
    0.80
    )>
    0.80
    ]}>
    0.79
    }}>
    0.79
    ()}>
    0.78
    .>
    0.74
    Act Density 0.144%

    No Known Activations