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

    Neuronpedia

    INDEX
    Explanations

    generating insights and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     avatars
    0.46
     natureza
    0.45
     libras
    0.45
     avail
    0.44
     bicarbon
    0.43
     persuade
    0.43
     obrigado
    0.43
     updates
    0.42
     Naira
    0.42
     stabilize
    0.42
    POSITIVE LOGITS
    考試
    0.44
    connecting
    0.41
    Connecting
    0.40
    ligne
    0.40
    高雄
    0.38
    Kline
    0.38
    ángulo
    0.38
    南極
    0.38
    <unused11>
    0.38
    個月
    0.37
    Act Density 0.003%

    No Known Activations