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

    Neuronpedia

    INDEX
    Explanations

    API calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     complètement
    0.75
    土地
    0.72
    ب
    0.72
    这样
    0.70
    те
    0.70
    1
    0.69
    cano
    0.68
    </em>
    0.67
    很难
    0.67
     vraiment
    0.67
    POSITIVE LOGITS
    𝗡
    0.96
     profissional
    0.95
     revisão
    0.93
     جوړونکو
    0.91
     geração
    0.91
     ماشینونه
    0.90
    ==============]
    0.90
     monolayers
    0.90
     nacionais
    0.90
     princípios
    0.89
    Act Density 0.000%

    No Known Activations