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

    Neuronpedia

    INDEX
    Explanations

    instances of introductory phrases or keywords that set the context for a document

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

    Code snippets and technical documentation fragments

    np_acts-logits-general · gemini-2.0-flash

    an office, land use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HandlerContext
    -0.57
     defStyle
    -0.54
    onAttach
    -0.52
    úgó
    -0.47
     gezet
    -0.47
     löyty
    -0.46
     fermés
    -0.46
     vediamo
    -0.45
     Duda
    -0.44
     cuales
    -0.44
    POSITIVE LOGITS
    TypedDataSet
    0.94
    aarrggbb
    0.76
    DebuggerStep
    0.74
    )}=\
    0.74
    ]})
    0.68
    )$}
    0.68
    (!__
    0.66
    */),
    0.66
    })$}
    0.65
    ')
    0.65
    Act Density 0.036%

    No Known Activations