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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming and technical language

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

    any direct binding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Educação
    -0.42
    いくつか
    -0.41
     antemano
    -0.40
     yeterli
    -0.40
     reducir
    -0.40
     reducido
    -0.39
     among
    -0.38
    Litteratur
    -0.38
     escase
    -0.38
     montanha
    -0.38
    POSITIVE LOGITS
     any
    0.62
    Any
    0.56
     Any
    0.56
     sekal
    0.55
    任何
    0.54
    RTLR
    0.54
    setVerticalGroup
    0.52
     любые
    0.52
     cualquier
    0.52
     apapun
    0.51
    Act Density 0.138%

    No Known Activations