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

    Neuronpedia

    INDEX
    Explanations

    new + places and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     new
    1.21
    new
    1.19
    新款
    0.99
     newer
    0.92
     nouvelle
    0.89
     новой
    0.86
     новую
    0.86
     nuove
    0.86
    在新
    0.85
     새로운
    0.84
    POSITIVE LOGITS
     york
    2.33
     zealand
    2.17
    york
    2.13
     York
    2.05
     Zealand
    2.01
    spapers
    2.01
    comer
    1.89
    York
    1.81
     सिरे
    1.81
    comers
    1.79
    Act Density 0.131%

    No Known Activations