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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating progression, conclusions, and the results of analyses or arguments

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

    Foreign language explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.57
    PreferredItem
    -0.57
    transQ
    -0.50
    oredCriteria
    -0.49
     समीक्षाओं
    -0.48
    AppBar
    -0.48
     purpoſe
    -0.48
    })()
    -0.47
    ButterKnife
    -0.47
    ')['
    -0.47
    POSITIVE LOGITS
     trámites
    0.38
     Freundschaft
    0.38
     restauración
    0.37
     llegada
    0.36
    脚注の使い方
    0.36
     esclavos
    0.35
     logros
    0.35
     Polize
    0.34
     avanzado
    0.34
     Verhandlungen
    0.33
    Act Density 0.254%

    No Known Activations