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

    Neuronpedia

    INDEX
    Explanations

    casual conversation openers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    न
    0.77
     Việc
    0.74
     geopolitical
    0.73
     রাজনৈতিক
    0.73
    ের
    0.71
    ↵
    0.71
     conceptions
    0.71
    ಲ್ಲಿ
    0.71
     katika
    0.71
     epistem
    0.71
    POSITIVE LOGITS
    ק
    0.91
    𝖔
    0.88
    𝓈
    0.79
    𝒽
    0.79
    ໋
    0.77
     乀
    0.76
    ᶰ
    0.76
    pf
    0.76
     infección
    0.75
    ❤️
    0.74
    Act Density 0.311%

    No Known Activations