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

    Neuronpedia

    INDEX
    Explanations

    something intended

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gerenci
    0.52
     கட்டமை
    0.52
     dédié
    0.50
     글로벌
    0.50
     granularity
    0.49
     سیستم
    0.47
     컬러
    0.47
     kiddos
    0.46
     Cortana
    0.46
     تطبيقات
    0.45
    POSITIVE LOGITS
     chiefly
    0.53
     usually
    0.46
     something
    0.44
     unusually
    0.43
     oneself
    0.43
    ឬ
    0.42
     एखाद्या
    0.42
    an
    0.42
     lessened
    0.42
    н
    0.42
    Act Density 0.175%

    No Known Activations